Merge branch 'gesen2egee/val' into validation-loss-upstream

Modified various implementations to restore original behavior

library/custom_train_functions.py

@@ -1,8 +1,16 @@
+from diffusers.schedulers.scheduling_ddpm import DDPMScheduler
 import torch
 import argparse
 import random
 import re
+from torch.types import Number
 from typing import List, Optional, Union
+from .utils import setup_logging
+
+setup_logging()
+import logging
+
+logger = logging.getLogger(__name__)
 
 
 def prepare_scheduler_for_custom_training(noise_scheduler, device):
@@ -21,7 +29,7 @@ def prepare_scheduler_for_custom_training(noise_scheduler, device):
 
 def fix_noise_scheduler_betas_for_zero_terminal_snr(noise_scheduler):
     # fix beta: zero terminal SNR
-    print(f"fix noise scheduler betas: https://arxiv.org/abs/2305.08891")
+    logger.info(f"fix noise scheduler betas: https://arxiv.org/abs/2305.08891")
 
     def enforce_zero_terminal_snr(betas):
         # Convert betas to alphas_bar_sqrt
@@ -49,50 +57,55 @@ def fix_noise_scheduler_betas_for_zero_terminal_snr(noise_scheduler):
     alphas = 1.0 - betas
     alphas_cumprod = torch.cumprod(alphas, dim=0)
 
-    # print("original:", noise_scheduler.betas)
-    # print("fixed:", betas)
+    # logger.info(f"original: {noise_scheduler.betas}")
+    # logger.info(f"fixed: {betas}")
 
     noise_scheduler.betas = betas
     noise_scheduler.alphas = alphas
     noise_scheduler.alphas_cumprod = alphas_cumprod
 
 
-def apply_snr_weight(loss, timesteps, noise_scheduler, gamma):
+def apply_snr_weight(loss: torch.Tensor, timesteps: torch.IntTensor, noise_scheduler: DDPMScheduler, gamma: Number, v_prediction=False):
     snr = torch.stack([noise_scheduler.all_snr[t] for t in timesteps])
-    gamma_over_snr = torch.div(torch.ones_like(snr) * gamma, snr)
-    snr_weight = torch.minimum(gamma_over_snr, torch.ones_like(gamma_over_snr)).float().to(loss.device)  # from paper
+    min_snr_gamma = torch.minimum(snr, torch.full_like(snr, gamma))
+    if v_prediction:
+        snr_weight = torch.div(min_snr_gamma, snr + 1).float().to(loss.device)
+    else:
+        snr_weight = torch.div(min_snr_gamma, snr).float().to(loss.device)
     loss = loss * snr_weight
     return loss
 
 
-def scale_v_prediction_loss_like_noise_prediction(loss, timesteps, noise_scheduler):
+def scale_v_prediction_loss_like_noise_prediction(loss: torch.Tensor, timesteps: torch.IntTensor, noise_scheduler: DDPMScheduler):
     scale = get_snr_scale(timesteps, noise_scheduler)
     loss = loss * scale
     return loss
 
 
-def get_snr_scale(timesteps, noise_scheduler):
+def get_snr_scale(timesteps: torch.IntTensor, noise_scheduler: DDPMScheduler):
     snr_t = torch.stack([noise_scheduler.all_snr[t] for t in timesteps])  # batch_size
     snr_t = torch.minimum(snr_t, torch.ones_like(snr_t) * 1000)  # if timestep is 0, snr_t is inf, so limit it to 1000
     scale = snr_t / (snr_t + 1)
     # # show debug info
-    # print(f"timesteps: {timesteps}, snr_t: {snr_t}, scale: {scale}")
+    # logger.info(f"timesteps: {timesteps}, snr_t: {snr_t}, scale: {scale}")
     return scale
 
 
-def add_v_prediction_like_loss(loss, timesteps, noise_scheduler, v_pred_like_loss):
+def add_v_prediction_like_loss(loss: torch.Tensor, timesteps: torch.IntTensor, noise_scheduler: DDPMScheduler, v_pred_like_loss: torch.Tensor):
     scale = get_snr_scale(timesteps, noise_scheduler)
-    # print(f"add v-prediction like loss: {v_pred_like_loss}, scale: {scale}, loss: {loss}, time: {timesteps}")
+    # logger.info(f"add v-prediction like loss: {v_pred_like_loss}, scale: {scale}, loss: {loss}, time: {timesteps}")
     loss = loss + loss / scale * v_pred_like_loss
     return loss
 
-def apply_debiased_estimation(loss, timesteps, noise_scheduler):
+
+def apply_debiased_estimation(loss: torch.Tensor, timesteps: torch.IntTensor, noise_scheduler: DDPMScheduler):
     snr_t = torch.stack([noise_scheduler.all_snr[t] for t in timesteps])  # batch_size
     snr_t = torch.minimum(snr_t, torch.ones_like(snr_t) * 1000)  # if timestep is 0, snr_t is inf, so limit it to 1000
-    weight = 1/torch.sqrt(snr_t)
+    weight = 1 / torch.sqrt(snr_t)
     loss = weight * loss
     return loss
 
+
 # TODO train_utilと分散しているのでどちらかに寄せる
 
 
@@ -265,7 +278,7 @@ def get_prompts_with_weights(tokenizer, prompt: List[str], max_length: int):
         tokens.append(text_token)
         weights.append(text_weight)
     if truncated:
-        print("Prompt was truncated. Try to shorten the prompt or increase max_embeddings_multiples")
+        logger.warning("Prompt was truncated. Try to shorten the prompt or increase max_embeddings_multiples")
     return tokens, weights
 
 
@@ -468,6 +481,17 @@ def apply_noise_offset(latents, noise, noise_offset, adaptive_noise_scale):
     return noise
 
 
+def apply_masked_loss(loss, batch):
+    # mask image is -1 to 1. we need to convert it to 0 to 1
+    mask_image = batch["conditioning_images"].to(dtype=loss.dtype)[:, 0].unsqueeze(1)  # use R channel
+
+    # resize to the same size as the loss
+    mask_image = torch.nn.functional.interpolate(mask_image, size=loss.shape[2:], mode="area")
+    mask_image = mask_image / 2 + 0.5
+    loss = loss * mask_image
+    return loss
+
+
 """
 ##########################################
 # Perlin Noise

library/deepspeed_utils.py

@@ -0,0 +1,139 @@
+import os
+import argparse
+import torch
+from accelerate import DeepSpeedPlugin, Accelerator
+
+from .utils import setup_logging
+
+setup_logging()
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+def add_deepspeed_arguments(parser: argparse.ArgumentParser):
+    # DeepSpeed Arguments. https://huggingface.co/docs/accelerate/usage_guides/deepspeed
+    parser.add_argument("--deepspeed", action="store_true", help="enable deepspeed training")
+    parser.add_argument("--zero_stage", type=int, default=2, choices=[0, 1, 2, 3], help="Possible options are 0,1,2,3.")
+    parser.add_argument(
+        "--offload_optimizer_device",
+        type=str,
+        default=None,
+        choices=[None, "cpu", "nvme"],
+        help="Possible options are none|cpu|nvme. Only applicable with ZeRO Stages 2 and 3.",
+    )
+    parser.add_argument(
+        "--offload_optimizer_nvme_path",
+        type=str,
+        default=None,
+        help="Possible options are /nvme|/local_nvme. Only applicable with ZeRO Stage 3.",
+    )
+    parser.add_argument(
+        "--offload_param_device",
+        type=str,
+        default=None,
+        choices=[None, "cpu", "nvme"],
+        help="Possible options are none|cpu|nvme. Only applicable with ZeRO Stage 3.",
+    )
+    parser.add_argument(
+        "--offload_param_nvme_path",
+        type=str,
+        default=None,
+        help="Possible options are /nvme|/local_nvme. Only applicable with ZeRO Stage 3.",
+    )
+    parser.add_argument(
+        "--zero3_init_flag",
+        action="store_true",
+        help="Flag to indicate whether to enable `deepspeed.zero.Init` for constructing massive models."
+        "Only applicable with ZeRO Stage-3.",
+    )
+    parser.add_argument(
+        "--zero3_save_16bit_model",
+        action="store_true",
+        help="Flag to indicate whether to save 16-bit model. Only applicable with ZeRO Stage-3.",
+    )
+    parser.add_argument(
+        "--fp16_master_weights_and_gradients",
+        action="store_true",
+        help="fp16_master_and_gradients requires optimizer to support keeping fp16 master and gradients while keeping the optimizer states in fp32.",
+    )
+
+
+def prepare_deepspeed_args(args: argparse.Namespace):
+    if not args.deepspeed:
+        return
+
+    # To avoid RuntimeError: DataLoader worker exited unexpectedly with exit code 1.
+    args.max_data_loader_n_workers = 1
+
+
+def prepare_deepspeed_plugin(args: argparse.Namespace):
+    if not args.deepspeed:
+        return None
+
+    try:
+        import deepspeed
+    except ImportError as e:
+        logger.error(
+            "deepspeed is not installed. please install deepspeed in your environment with following command. DS_BUILD_OPS=0 pip install deepspeed"
+        )
+        exit(1)
+
+    deepspeed_plugin = DeepSpeedPlugin(
+        zero_stage=args.zero_stage,
+        gradient_accumulation_steps=args.gradient_accumulation_steps,
+        gradient_clipping=args.max_grad_norm,
+        offload_optimizer_device=args.offload_optimizer_device,
+        offload_optimizer_nvme_path=args.offload_optimizer_nvme_path,
+        offload_param_device=args.offload_param_device,
+        offload_param_nvme_path=args.offload_param_nvme_path,
+        zero3_init_flag=args.zero3_init_flag,
+        zero3_save_16bit_model=args.zero3_save_16bit_model,
+    )
+    deepspeed_plugin.deepspeed_config["train_micro_batch_size_per_gpu"] = args.train_batch_size
+    deepspeed_plugin.deepspeed_config["train_batch_size"] = (
+        args.train_batch_size * args.gradient_accumulation_steps * int(os.environ["WORLD_SIZE"])
+    )
+    deepspeed_plugin.set_mixed_precision(args.mixed_precision)
+    if args.mixed_precision.lower() == "fp16":
+        deepspeed_plugin.deepspeed_config["fp16"]["initial_scale_power"] = 0  # preventing overflow.
+    if args.full_fp16 or args.fp16_master_weights_and_gradients:
+        if args.offload_optimizer_device == "cpu" and args.zero_stage == 2:
+            deepspeed_plugin.deepspeed_config["fp16"]["fp16_master_weights_and_grads"] = True
+            logger.info("[DeepSpeed] full fp16 enable.")
+        else:
+            logger.info(
+                "[DeepSpeed]full fp16, fp16_master_weights_and_grads currently only supported using ZeRO-Offload with DeepSpeedCPUAdam on ZeRO-2 stage."
+            )
+
+    if args.offload_optimizer_device is not None:
+        logger.info("[DeepSpeed] start to manually build cpu_adam.")
+        deepspeed.ops.op_builder.CPUAdamBuilder().load()
+        logger.info("[DeepSpeed] building cpu_adam done.")
+
+    return deepspeed_plugin
+
+
+# Accelerate library does not support multiple models for deepspeed. So, we need to wrap multiple models into a single model.
+def prepare_deepspeed_model(args: argparse.Namespace, **models):
+    # remove None from models
+    models = {k: v for k, v in models.items() if v is not None}
+
+    class DeepSpeedWrapper(torch.nn.Module):
+        def __init__(self, **kw_models) -> None:
+            super().__init__()
+            self.models = torch.nn.ModuleDict()
+
+            for key, model in kw_models.items():
+                if isinstance(model, list):
+                    model = torch.nn.ModuleList(model)
+                assert isinstance(
+                    model, torch.nn.Module
+                ), f"model must be an instance of torch.nn.Module, but got {key} is {type(model)}"
+                self.models.update(torch.nn.ModuleDict({key: model}))
+
+        def get_models(self):
+            return self.models
+
+    ds_model = DeepSpeedWrapper(**models)
+    return ds_model

library/device_utils.py

@@ -0,0 +1,84 @@
+import functools
+import gc
+
+import torch
+
+try:
+    HAS_CUDA = torch.cuda.is_available()
+except Exception:
+    HAS_CUDA = False
+
+try:
+    HAS_MPS = torch.backends.mps.is_available()
+except Exception:
+    HAS_MPS = False
+
+try:
+    import intel_extension_for_pytorch as ipex  # noqa
+
+    HAS_XPU = torch.xpu.is_available()
+except Exception:
+    HAS_XPU = False
+
+
+def clean_memory():
+    gc.collect()
+    if HAS_CUDA:
+        torch.cuda.empty_cache()
+    if HAS_XPU:
+        torch.xpu.empty_cache()
+    if HAS_MPS:
+        torch.mps.empty_cache()
+
+
+def clean_memory_on_device(device: torch.device):
+    r"""
+    Clean memory on the specified device, will be called from training scripts.
+    """
+    gc.collect()
+
+    # device may "cuda" or "cuda:0", so we need to check the type of device
+    if device.type == "cuda":
+        torch.cuda.empty_cache()
+    if device.type == "xpu":
+        torch.xpu.empty_cache()
+    if device.type == "mps":
+        torch.mps.empty_cache()
+
+
+@functools.lru_cache(maxsize=None)
+def get_preferred_device() -> torch.device:
+    r"""
+    Do not call this function from training scripts. Use accelerator.device instead.
+    """
+    if HAS_CUDA:
+        device = torch.device("cuda")
+    elif HAS_XPU:
+        device = torch.device("xpu")
+    elif HAS_MPS:
+        device = torch.device("mps")
+    else:
+        device = torch.device("cpu")
+    print(f"get_preferred_device() -> {device}")
+    return device
+
+
+def init_ipex():
+    """
+    Apply IPEX to CUDA hijacks using `library.ipex.ipex_init`.
+
+    This function should run right after importing torch and before doing anything else.
+
+    If IPEX is not available, this function does nothing.
+    """
+    try:
+        if HAS_XPU:
+            from library.ipex import ipex_init
+
+            is_initialized, error_message = ipex_init()
+            if not is_initialized:
+                print("failed to initialize ipex:", error_message)
+        else:
+            return
+    except Exception as e:
+        print("failed to initialize ipex:", e)

library/huggingface_util.py

@@ -4,7 +4,10 @@ from pathlib import Path
 import argparse
 import os
 from library.utils import fire_in_thread
-
+from library.utils import setup_logging
+setup_logging()
+import logging
+logger = logging.getLogger(__name__)
 
 def exists_repo(repo_id: str, repo_type: str, revision: str = "main", token: str = None):
     api = HfApi(
@@ -33,9 +36,9 @@ def upload(
         try:
             api.create_repo(repo_id=repo_id, repo_type=repo_type, private=private)
         except Exception as e:  # とりあえずRepositoryNotFoundErrorは確認したが他にあると困るので
-            print("===========================================")
-            print(f"failed to create HuggingFace repo / HuggingFaceのリポジトリの作成に失敗しました : {e}")
-            print("===========================================")
+            logger.error("===========================================")
+            logger.error(f"failed to create HuggingFace repo / HuggingFaceのリポジトリの作成に失敗しました : {e}")
+            logger.error("===========================================")
 
     is_folder = (type(src) == str and os.path.isdir(src)) or (isinstance(src, Path) and src.is_dir())
 
@@ -56,9 +59,9 @@ def upload(
                     path_in_repo=path_in_repo,
                 )
         except Exception as e:  # RuntimeErrorを確認済みだが他にあると困るので
-            print("===========================================")
-            print(f"failed to upload to HuggingFace / HuggingFaceへのアップロードに失敗しました : {e}")
-            print("===========================================")
+            logger.error("===========================================")
+            logger.error(f"failed to upload to HuggingFace / HuggingFaceへのアップロードに失敗しました : {e}")
+            logger.error("===========================================")
 
     if args.async_upload and not force_sync_upload:
         fire_in_thread(uploader)

library/ipex/__init__.py

@@ -4,172 +4,177 @@ import contextlib
 import torch
 import intel_extension_for_pytorch as ipex # pylint: disable=import-error, unused-import
 from .hijacks import ipex_hijacks
-from .attention import attention_init
 
 # pylint: disable=protected-access, missing-function-docstring, line-too-long
 
 def ipex_init(): # pylint: disable=too-many-statements
     try:
-        #Replace cuda with xpu:
-        torch.cuda.current_device = torch.xpu.current_device
-        torch.cuda.current_stream = torch.xpu.current_stream
-        torch.cuda.device = torch.xpu.device
-        torch.cuda.device_count = torch.xpu.device_count
-        torch.cuda.device_of = torch.xpu.device_of
-        torch.cuda.get_device_name = torch.xpu.get_device_name
-        torch.cuda.get_device_properties = torch.xpu.get_device_properties
-        torch.cuda.init = torch.xpu.init
-        torch.cuda.is_available = torch.xpu.is_available
-        torch.cuda.is_initialized = torch.xpu.is_initialized
-        torch.cuda.is_current_stream_capturing = lambda: False
-        torch.cuda.set_device = torch.xpu.set_device
-        torch.cuda.stream = torch.xpu.stream
-        torch.cuda.synchronize = torch.xpu.synchronize
-        torch.cuda.Event = torch.xpu.Event
-        torch.cuda.Stream = torch.xpu.Stream
-        torch.cuda.FloatTensor = torch.xpu.FloatTensor
-        torch.Tensor.cuda = torch.Tensor.xpu
-        torch.Tensor.is_cuda = torch.Tensor.is_xpu
-        torch.cuda._initialization_lock = torch.xpu.lazy_init._initialization_lock
-        torch.cuda._initialized = torch.xpu.lazy_init._initialized
-        torch.cuda._lazy_seed_tracker = torch.xpu.lazy_init._lazy_seed_tracker
-        torch.cuda._queued_calls = torch.xpu.lazy_init._queued_calls
-        torch.cuda._tls = torch.xpu.lazy_init._tls
-        torch.cuda.threading = torch.xpu.lazy_init.threading
-        torch.cuda.traceback = torch.xpu.lazy_init.traceback
-        torch.cuda.Optional = torch.xpu.Optional
-        torch.cuda.__cached__ = torch.xpu.__cached__
-        torch.cuda.__loader__ = torch.xpu.__loader__
-        torch.cuda.ComplexFloatStorage = torch.xpu.ComplexFloatStorage
-        torch.cuda.Tuple = torch.xpu.Tuple
-        torch.cuda.streams = torch.xpu.streams
-        torch.cuda._lazy_new = torch.xpu._lazy_new
-        torch.cuda.FloatStorage = torch.xpu.FloatStorage
-        torch.cuda.Any = torch.xpu.Any
-        torch.cuda.__doc__ = torch.xpu.__doc__
-        torch.cuda.default_generators = torch.xpu.default_generators
-        torch.cuda.HalfTensor = torch.xpu.HalfTensor
-        torch.cuda._get_device_index = torch.xpu._get_device_index
-        torch.cuda.__path__ = torch.xpu.__path__
-        torch.cuda.Device = torch.xpu.Device
-        torch.cuda.IntTensor = torch.xpu.IntTensor
-        torch.cuda.ByteStorage = torch.xpu.ByteStorage
-        torch.cuda.set_stream = torch.xpu.set_stream
-        torch.cuda.BoolStorage = torch.xpu.BoolStorage
-        torch.cuda.os = torch.xpu.os
-        torch.cuda.torch = torch.xpu.torch
-        torch.cuda.BFloat16Storage = torch.xpu.BFloat16Storage
-        torch.cuda.Union = torch.xpu.Union
-        torch.cuda.DoubleTensor = torch.xpu.DoubleTensor
-        torch.cuda.ShortTensor = torch.xpu.ShortTensor
-        torch.cuda.LongTensor = torch.xpu.LongTensor
-        torch.cuda.IntStorage = torch.xpu.IntStorage
-        torch.cuda.LongStorage = torch.xpu.LongStorage
-        torch.cuda.__annotations__ = torch.xpu.__annotations__
-        torch.cuda.__package__ = torch.xpu.__package__
-        torch.cuda.__builtins__ = torch.xpu.__builtins__
-        torch.cuda.CharTensor = torch.xpu.CharTensor
-        torch.cuda.List = torch.xpu.List
-        torch.cuda._lazy_init = torch.xpu._lazy_init
-        torch.cuda.BFloat16Tensor = torch.xpu.BFloat16Tensor
-        torch.cuda.DoubleStorage = torch.xpu.DoubleStorage
-        torch.cuda.ByteTensor = torch.xpu.ByteTensor
-        torch.cuda.StreamContext = torch.xpu.StreamContext
-        torch.cuda.ComplexDoubleStorage = torch.xpu.ComplexDoubleStorage
-        torch.cuda.ShortStorage = torch.xpu.ShortStorage
-        torch.cuda._lazy_call = torch.xpu._lazy_call
-        torch.cuda.HalfStorage = torch.xpu.HalfStorage
-        torch.cuda.random = torch.xpu.random
-        torch.cuda._device = torch.xpu._device
-        torch.cuda.classproperty = torch.xpu.classproperty
-        torch.cuda.__name__ = torch.xpu.__name__
-        torch.cuda._device_t = torch.xpu._device_t
-        torch.cuda.warnings = torch.xpu.warnings
-        torch.cuda.__spec__ = torch.xpu.__spec__
-        torch.cuda.BoolTensor = torch.xpu.BoolTensor
-        torch.cuda.CharStorage = torch.xpu.CharStorage
-        torch.cuda.__file__ = torch.xpu.__file__
-        torch.cuda._is_in_bad_fork = torch.xpu.lazy_init._is_in_bad_fork
-        #torch.cuda.is_current_stream_capturing = torch.xpu.is_current_stream_capturing
+        if hasattr(torch, "cuda") and hasattr(torch.cuda, "is_xpu_hijacked") and torch.cuda.is_xpu_hijacked:
+            return True, "Skipping IPEX hijack"
+        else:
+            # Replace cuda with xpu:
+            torch.cuda.current_device = torch.xpu.current_device
+            torch.cuda.current_stream = torch.xpu.current_stream
+            torch.cuda.device = torch.xpu.device
+            torch.cuda.device_count = torch.xpu.device_count
+            torch.cuda.device_of = torch.xpu.device_of
+            torch.cuda.get_device_name = torch.xpu.get_device_name
+            torch.cuda.get_device_properties = torch.xpu.get_device_properties
+            torch.cuda.init = torch.xpu.init
+            torch.cuda.is_available = torch.xpu.is_available
+            torch.cuda.is_initialized = torch.xpu.is_initialized
+            torch.cuda.is_current_stream_capturing = lambda: False
+            torch.cuda.set_device = torch.xpu.set_device
+            torch.cuda.stream = torch.xpu.stream
+            torch.cuda.synchronize = torch.xpu.synchronize
+            torch.cuda.Event = torch.xpu.Event
+            torch.cuda.Stream = torch.xpu.Stream
+            torch.cuda.FloatTensor = torch.xpu.FloatTensor
+            torch.Tensor.cuda = torch.Tensor.xpu
+            torch.Tensor.is_cuda = torch.Tensor.is_xpu
+            torch.nn.Module.cuda = torch.nn.Module.xpu
+            torch.UntypedStorage.cuda = torch.UntypedStorage.xpu
+            torch.cuda._initialization_lock = torch.xpu.lazy_init._initialization_lock
+            torch.cuda._initialized = torch.xpu.lazy_init._initialized
+            torch.cuda._lazy_seed_tracker = torch.xpu.lazy_init._lazy_seed_tracker
+            torch.cuda._queued_calls = torch.xpu.lazy_init._queued_calls
+            torch.cuda._tls = torch.xpu.lazy_init._tls
+            torch.cuda.threading = torch.xpu.lazy_init.threading
+            torch.cuda.traceback = torch.xpu.lazy_init.traceback
+            torch.cuda.Optional = torch.xpu.Optional
+            torch.cuda.__cached__ = torch.xpu.__cached__
+            torch.cuda.__loader__ = torch.xpu.__loader__
+            torch.cuda.ComplexFloatStorage = torch.xpu.ComplexFloatStorage
+            torch.cuda.Tuple = torch.xpu.Tuple
+            torch.cuda.streams = torch.xpu.streams
+            torch.cuda._lazy_new = torch.xpu._lazy_new
+            torch.cuda.FloatStorage = torch.xpu.FloatStorage
+            torch.cuda.Any = torch.xpu.Any
+            torch.cuda.__doc__ = torch.xpu.__doc__
+            torch.cuda.default_generators = torch.xpu.default_generators
+            torch.cuda.HalfTensor = torch.xpu.HalfTensor
+            torch.cuda._get_device_index = torch.xpu._get_device_index
+            torch.cuda.__path__ = torch.xpu.__path__
+            torch.cuda.Device = torch.xpu.Device
+            torch.cuda.IntTensor = torch.xpu.IntTensor
+            torch.cuda.ByteStorage = torch.xpu.ByteStorage
+            torch.cuda.set_stream = torch.xpu.set_stream
+            torch.cuda.BoolStorage = torch.xpu.BoolStorage
+            torch.cuda.os = torch.xpu.os
+            torch.cuda.torch = torch.xpu.torch
+            torch.cuda.BFloat16Storage = torch.xpu.BFloat16Storage
+            torch.cuda.Union = torch.xpu.Union
+            torch.cuda.DoubleTensor = torch.xpu.DoubleTensor
+            torch.cuda.ShortTensor = torch.xpu.ShortTensor
+            torch.cuda.LongTensor = torch.xpu.LongTensor
+            torch.cuda.IntStorage = torch.xpu.IntStorage
+            torch.cuda.LongStorage = torch.xpu.LongStorage
+            torch.cuda.__annotations__ = torch.xpu.__annotations__
+            torch.cuda.__package__ = torch.xpu.__package__
+            torch.cuda.__builtins__ = torch.xpu.__builtins__
+            torch.cuda.CharTensor = torch.xpu.CharTensor
+            torch.cuda.List = torch.xpu.List
+            torch.cuda._lazy_init = torch.xpu._lazy_init
+            torch.cuda.BFloat16Tensor = torch.xpu.BFloat16Tensor
+            torch.cuda.DoubleStorage = torch.xpu.DoubleStorage
+            torch.cuda.ByteTensor = torch.xpu.ByteTensor
+            torch.cuda.StreamContext = torch.xpu.StreamContext
+            torch.cuda.ComplexDoubleStorage = torch.xpu.ComplexDoubleStorage
+            torch.cuda.ShortStorage = torch.xpu.ShortStorage
+            torch.cuda._lazy_call = torch.xpu._lazy_call
+            torch.cuda.HalfStorage = torch.xpu.HalfStorage
+            torch.cuda.random = torch.xpu.random
+            torch.cuda._device = torch.xpu._device
+            torch.cuda.classproperty = torch.xpu.classproperty
+            torch.cuda.__name__ = torch.xpu.__name__
+            torch.cuda._device_t = torch.xpu._device_t
+            torch.cuda.warnings = torch.xpu.warnings
+            torch.cuda.__spec__ = torch.xpu.__spec__
+            torch.cuda.BoolTensor = torch.xpu.BoolTensor
+            torch.cuda.CharStorage = torch.xpu.CharStorage
+            torch.cuda.__file__ = torch.xpu.__file__
+            torch.cuda._is_in_bad_fork = torch.xpu.lazy_init._is_in_bad_fork
+            # torch.cuda.is_current_stream_capturing = torch.xpu.is_current_stream_capturing
 
-        #Memory:
-        torch.cuda.memory = torch.xpu.memory
-        if 'linux' in sys.platform and "WSL2" in os.popen("uname -a").read():
-            torch.xpu.empty_cache = lambda: None
-        torch.cuda.empty_cache = torch.xpu.empty_cache
-        torch.cuda.memory_stats = torch.xpu.memory_stats
-        torch.cuda.memory_summary = torch.xpu.memory_summary
-        torch.cuda.memory_snapshot = torch.xpu.memory_snapshot
-        torch.cuda.memory_allocated = torch.xpu.memory_allocated
-        torch.cuda.max_memory_allocated = torch.xpu.max_memory_allocated
-        torch.cuda.memory_reserved = torch.xpu.memory_reserved
-        torch.cuda.memory_cached = torch.xpu.memory_reserved
-        torch.cuda.max_memory_reserved = torch.xpu.max_memory_reserved
-        torch.cuda.max_memory_cached = torch.xpu.max_memory_reserved
-        torch.cuda.reset_peak_memory_stats = torch.xpu.reset_peak_memory_stats
-        torch.cuda.reset_max_memory_cached = torch.xpu.reset_peak_memory_stats
-        torch.cuda.reset_max_memory_allocated = torch.xpu.reset_peak_memory_stats
-        torch.cuda.memory_stats_as_nested_dict = torch.xpu.memory_stats_as_nested_dict
-        torch.cuda.reset_accumulated_memory_stats = torch.xpu.reset_accumulated_memory_stats
+            # Memory:
+            torch.cuda.memory = torch.xpu.memory
+            if 'linux' in sys.platform and "WSL2" in os.popen("uname -a").read():
+                torch.xpu.empty_cache = lambda: None
+            torch.cuda.empty_cache = torch.xpu.empty_cache
+            torch.cuda.memory_stats = torch.xpu.memory_stats
+            torch.cuda.memory_summary = torch.xpu.memory_summary
+            torch.cuda.memory_snapshot = torch.xpu.memory_snapshot
+            torch.cuda.memory_allocated = torch.xpu.memory_allocated
+            torch.cuda.max_memory_allocated = torch.xpu.max_memory_allocated
+            torch.cuda.memory_reserved = torch.xpu.memory_reserved
+            torch.cuda.memory_cached = torch.xpu.memory_reserved
+            torch.cuda.max_memory_reserved = torch.xpu.max_memory_reserved
+            torch.cuda.max_memory_cached = torch.xpu.max_memory_reserved
+            torch.cuda.reset_peak_memory_stats = torch.xpu.reset_peak_memory_stats
+            torch.cuda.reset_max_memory_cached = torch.xpu.reset_peak_memory_stats
+            torch.cuda.reset_max_memory_allocated = torch.xpu.reset_peak_memory_stats
+            torch.cuda.memory_stats_as_nested_dict = torch.xpu.memory_stats_as_nested_dict
+            torch.cuda.reset_accumulated_memory_stats = torch.xpu.reset_accumulated_memory_stats
 
-        #RNG:
-        torch.cuda.get_rng_state = torch.xpu.get_rng_state
-        torch.cuda.get_rng_state_all = torch.xpu.get_rng_state_all
-        torch.cuda.set_rng_state = torch.xpu.set_rng_state
-        torch.cuda.set_rng_state_all = torch.xpu.set_rng_state_all
-        torch.cuda.manual_seed = torch.xpu.manual_seed
-        torch.cuda.manual_seed_all = torch.xpu.manual_seed_all
-        torch.cuda.seed = torch.xpu.seed
-        torch.cuda.seed_all = torch.xpu.seed_all
-        torch.cuda.initial_seed = torch.xpu.initial_seed
+            # RNG:
+            torch.cuda.get_rng_state = torch.xpu.get_rng_state
+            torch.cuda.get_rng_state_all = torch.xpu.get_rng_state_all
+            torch.cuda.set_rng_state = torch.xpu.set_rng_state
+            torch.cuda.set_rng_state_all = torch.xpu.set_rng_state_all
+            torch.cuda.manual_seed = torch.xpu.manual_seed
+            torch.cuda.manual_seed_all = torch.xpu.manual_seed_all
+            torch.cuda.seed = torch.xpu.seed
+            torch.cuda.seed_all = torch.xpu.seed_all
+            torch.cuda.initial_seed = torch.xpu.initial_seed
+
+            # AMP:
+            torch.cuda.amp = torch.xpu.amp
+            torch.is_autocast_enabled = torch.xpu.is_autocast_xpu_enabled
+            torch.get_autocast_gpu_dtype = torch.xpu.get_autocast_xpu_dtype
+
+            if not hasattr(torch.cuda.amp, "common"):
+                torch.cuda.amp.common = contextlib.nullcontext()
+            torch.cuda.amp.common.amp_definitely_not_available = lambda: False
 
-        #AMP:
-        torch.cuda.amp = torch.xpu.amp
-        if not hasattr(torch.cuda.amp, "common"):
-            torch.cuda.amp.common = contextlib.nullcontext()
-        torch.cuda.amp.common.amp_definitely_not_available = lambda: False
-        try:
-            torch.cuda.amp.GradScaler = torch.xpu.amp.GradScaler
-        except Exception: # pylint: disable=broad-exception-caught
             try:
-                from .gradscaler import gradscaler_init # pylint: disable=import-outside-toplevel, import-error
-                gradscaler_init()
                 torch.cuda.amp.GradScaler = torch.xpu.amp.GradScaler
             except Exception: # pylint: disable=broad-exception-caught
-                torch.cuda.amp.GradScaler = ipex.cpu.autocast._grad_scaler.GradScaler
+                try:
+                    from .gradscaler import gradscaler_init # pylint: disable=import-outside-toplevel, import-error
+                    gradscaler_init()
+                    torch.cuda.amp.GradScaler = torch.xpu.amp.GradScaler
+                except Exception: # pylint: disable=broad-exception-caught
+                    torch.cuda.amp.GradScaler = ipex.cpu.autocast._grad_scaler.GradScaler
 
-        #C
-        torch._C._cuda_getCurrentRawStream = ipex._C._getCurrentStream
-        ipex._C._DeviceProperties.major = 2023
-        ipex._C._DeviceProperties.minor = 2
+            # C
+            torch._C._cuda_getCurrentRawStream = ipex._C._getCurrentStream
+            ipex._C._DeviceProperties.multi_processor_count = ipex._C._DeviceProperties.gpu_subslice_count
+            ipex._C._DeviceProperties.major = 2024
+            ipex._C._DeviceProperties.minor = 0
 
-        #Fix functions with ipex:
-        torch.cuda.mem_get_info = lambda device=None: [(torch.xpu.get_device_properties(device).total_memory - torch.xpu.memory_reserved(device)), torch.xpu.get_device_properties(device).total_memory]
-        torch._utils._get_available_device_type = lambda: "xpu"
-        torch.has_cuda = True
-        torch.cuda.has_half = True
-        torch.cuda.is_bf16_supported = lambda *args, **kwargs: True
-        torch.cuda.is_fp16_supported = lambda *args, **kwargs: True
-        torch.version.cuda = "11.7"
-        torch.cuda.get_device_capability = lambda *args, **kwargs: [11,7]
-        torch.cuda.get_device_properties.major = 11
-        torch.cuda.get_device_properties.minor = 7
-        torch.cuda.ipc_collect = lambda *args, **kwargs: None
-        torch.cuda.utilization = lambda *args, **kwargs: 0
-        if hasattr(torch.xpu, 'getDeviceIdListForCard'):
-            torch.cuda.getDeviceIdListForCard = torch.xpu.getDeviceIdListForCard
-            torch.cuda.get_device_id_list_per_card = torch.xpu.getDeviceIdListForCard
-        else:
-            torch.cuda.getDeviceIdListForCard = torch.xpu.get_device_id_list_per_card
-            torch.cuda.get_device_id_list_per_card = torch.xpu.get_device_id_list_per_card
+            # Fix functions with ipex:
+            torch.cuda.mem_get_info = lambda device=None: [(torch.xpu.get_device_properties(device).total_memory - torch.xpu.memory_reserved(device)), torch.xpu.get_device_properties(device).total_memory]
+            torch._utils._get_available_device_type = lambda: "xpu"
+            torch.has_cuda = True
+            torch.cuda.has_half = True
+            torch.cuda.is_bf16_supported = lambda *args, **kwargs: True
+            torch.cuda.is_fp16_supported = lambda *args, **kwargs: True
+            torch.backends.cuda.is_built = lambda *args, **kwargs: True
+            torch.version.cuda = "12.1"
+            torch.cuda.get_device_capability = lambda *args, **kwargs: [12,1]
+            torch.cuda.get_device_properties.major = 12
+            torch.cuda.get_device_properties.minor = 1
+            torch.cuda.ipc_collect = lambda *args, **kwargs: None
+            torch.cuda.utilization = lambda *args, **kwargs: 0
 
-        ipex_hijacks()
-        attention_init()
-        try:
-            from .diffusers import ipex_diffusers
-            ipex_diffusers()
-        except Exception: # pylint: disable=broad-exception-caught
-            pass
+            ipex_hijacks()
+            if not torch.xpu.has_fp64_dtype() or os.environ.get('IPEX_FORCE_ATTENTION_SLICE', None) is not None:
+                try:
+                    from .diffusers import ipex_diffusers
+                    ipex_diffusers()
+                except Exception: # pylint: disable=broad-exception-caught
+                    pass
+            torch.cuda.is_xpu_hijacked = True
     except Exception as e:
         return False, e
     return True, None

library/ipex/attention.py

@@ -1,45 +1,98 @@
+import os
 import torch
 import intel_extension_for_pytorch as ipex # pylint: disable=import-error, unused-import
+from functools import cache
 
 # pylint: disable=protected-access, missing-function-docstring, line-too-long
 
-original_torch_bmm = torch.bmm
-def torch_bmm(input, mat2, *, out=None):
-    if input.dtype != mat2.dtype:
-        mat2 = mat2.to(input.dtype)
+# ARC GPUs can't allocate more than 4GB to a single block so we slice the attetion layers
 
-    #ARC GPUs can't allocate more than 4GB to a single block, Slice it:
-    batch_size_attention, input_tokens, mat2_shape = input.shape[0], input.shape[1], mat2.shape[2]
-    block_multiply = input.element_size()
-    slice_block_size = input_tokens * mat2_shape / 1024 / 1024 * block_multiply
+sdpa_slice_trigger_rate = float(os.environ.get('IPEX_SDPA_SLICE_TRIGGER_RATE', 4))
+attention_slice_rate = float(os.environ.get('IPEX_ATTENTION_SLICE_RATE', 4))
+
+# Find something divisible with the input_tokens
+@cache
+def find_slice_size(slice_size, slice_block_size):
+    while (slice_size * slice_block_size) > attention_slice_rate:
+        slice_size = slice_size // 2
+        if slice_size <= 1:
+            slice_size = 1
+            break
+    return slice_size
+
+# Find slice sizes for SDPA
+@cache
+def find_sdpa_slice_sizes(query_shape, query_element_size):
+    if len(query_shape) == 3:
+        batch_size_attention, query_tokens, shape_three = query_shape
+        shape_four = 1
+    else:
+        batch_size_attention, query_tokens, shape_three, shape_four = query_shape
+
+    slice_block_size = query_tokens * shape_three * shape_four / 1024 / 1024 * query_element_size
     block_size = batch_size_attention * slice_block_size
 
     split_slice_size = batch_size_attention
-    if block_size > 4:
+    split_2_slice_size = query_tokens
+    split_3_slice_size = shape_three
+
+    do_split = False
+    do_split_2 = False
+    do_split_3 = False
+
+    if block_size > sdpa_slice_trigger_rate:
         do_split = True
-        #Find something divisible with the input_tokens
-        while (split_slice_size * slice_block_size) > 4:
-            split_slice_size = split_slice_size // 2
-            if split_slice_size <= 1:
-                split_slice_size = 1
-                break
-    else:
-        do_split = False
+        split_slice_size = find_slice_size(split_slice_size, slice_block_size)
+        if split_slice_size * slice_block_size > attention_slice_rate:
+            slice_2_block_size = split_slice_size * shape_three * shape_four / 1024 / 1024 * query_element_size
+            do_split_2 = True
+            split_2_slice_size = find_slice_size(split_2_slice_size, slice_2_block_size)
+            if split_2_slice_size * slice_2_block_size > attention_slice_rate:
+                slice_3_block_size = split_slice_size * split_2_slice_size * shape_four / 1024 / 1024 * query_element_size
+                do_split_3 = True
+                split_3_slice_size = find_slice_size(split_3_slice_size, slice_3_block_size)
 
+    return do_split, do_split_2, do_split_3, split_slice_size, split_2_slice_size, split_3_slice_size
+
+# Find slice sizes for BMM
+@cache
+def find_bmm_slice_sizes(input_shape, input_element_size, mat2_shape):
+    batch_size_attention, input_tokens, mat2_atten_shape = input_shape[0], input_shape[1], mat2_shape[2]
+    slice_block_size = input_tokens * mat2_atten_shape / 1024 / 1024 * input_element_size
+    block_size = batch_size_attention * slice_block_size
+
+    split_slice_size = batch_size_attention
     split_2_slice_size = input_tokens
-    if split_slice_size * slice_block_size > 4:
-        slice_block_size2 = split_slice_size * mat2_shape / 1024 / 1024 * block_multiply
-        do_split_2 = True
-        #Find something divisible with the input_tokens
-        while (split_2_slice_size * slice_block_size2) > 4:
-            split_2_slice_size = split_2_slice_size // 2
-            if split_2_slice_size <= 1:
-                split_2_slice_size = 1
-                break
-    else:
-        do_split_2 = False
+    split_3_slice_size = mat2_atten_shape
 
+    do_split = False
+    do_split_2 = False
+    do_split_3 = False
+
+    if block_size > attention_slice_rate:
+        do_split = True
+        split_slice_size = find_slice_size(split_slice_size, slice_block_size)
+        if split_slice_size * slice_block_size > attention_slice_rate:
+            slice_2_block_size = split_slice_size * mat2_atten_shape / 1024 / 1024 * input_element_size
+            do_split_2 = True
+            split_2_slice_size = find_slice_size(split_2_slice_size, slice_2_block_size)
+            if split_2_slice_size * slice_2_block_size > attention_slice_rate:
+                slice_3_block_size = split_slice_size * split_2_slice_size / 1024 / 1024 * input_element_size
+                do_split_3 = True
+                split_3_slice_size = find_slice_size(split_3_slice_size, slice_3_block_size)
+
+    return do_split, do_split_2, do_split_3, split_slice_size, split_2_slice_size, split_3_slice_size
+
+
+original_torch_bmm = torch.bmm
+def torch_bmm_32_bit(input, mat2, *, out=None):
+    if input.device.type != "xpu":
+        return original_torch_bmm(input, mat2, out=out)
+    do_split, do_split_2, do_split_3, split_slice_size, split_2_slice_size, split_3_slice_size = find_bmm_slice_sizes(input.shape, input.element_size(), mat2.shape)
+
+    # Slice BMM
     if do_split:
+        batch_size_attention, input_tokens, mat2_atten_shape = input.shape[0], input.shape[1], mat2.shape[2]
         hidden_states = torch.zeros(input.shape[0], input.shape[1], mat2.shape[2], device=input.device, dtype=input.dtype)
         for i in range(batch_size_attention // split_slice_size):
             start_idx = i * split_slice_size
@@ -48,62 +101,41 @@ def torch_bmm(input, mat2, *, out=None):
                 for i2 in range(input_tokens // split_2_slice_size): # pylint: disable=invalid-name
                     start_idx_2 = i2 * split_2_slice_size
                     end_idx_2 = (i2 + 1) * split_2_slice_size
-                    hidden_states[start_idx:end_idx, start_idx_2:end_idx_2] = original_torch_bmm(
-                        input[start_idx:end_idx, start_idx_2:end_idx_2],
-                        mat2[start_idx:end_idx, start_idx_2:end_idx_2],
-                        out=out
-                    )
+                    if do_split_3:
+                        for i3 in range(mat2_atten_shape // split_3_slice_size): # pylint: disable=invalid-name
+                            start_idx_3 = i3 * split_3_slice_size
+                            end_idx_3 = (i3 + 1) * split_3_slice_size
+                            hidden_states[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3] = original_torch_bmm(
+                                input[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3],
+                                mat2[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3],
+                                out=out
+                            )
+                    else:
+                        hidden_states[start_idx:end_idx, start_idx_2:end_idx_2] = original_torch_bmm(
+                            input[start_idx:end_idx, start_idx_2:end_idx_2],
+                            mat2[start_idx:end_idx, start_idx_2:end_idx_2],
+                            out=out
+                        )
             else:
                 hidden_states[start_idx:end_idx] = original_torch_bmm(
                     input[start_idx:end_idx],
                     mat2[start_idx:end_idx],
                     out=out
                 )
+        torch.xpu.synchronize(input.device)
     else:
         return original_torch_bmm(input, mat2, out=out)
     return hidden_states
 
 original_scaled_dot_product_attention = torch.nn.functional.scaled_dot_product_attention
-def scaled_dot_product_attention(query, key, value, attn_mask=None, dropout_p=0.0, is_causal=False):
-    #ARC GPUs can't allocate more than 4GB to a single block, Slice it:
-    if len(query.shape) == 3:
-        batch_size_attention, query_tokens, shape_four = query.shape
-        shape_one = 1
-        no_shape_one = True
-    else:
-        shape_one, batch_size_attention, query_tokens, shape_four = query.shape
-        no_shape_one = False
-
-    block_multiply = query.element_size()
-    slice_block_size = shape_one * query_tokens * shape_four / 1024 / 1024 * block_multiply
-    block_size = batch_size_attention * slice_block_size
-
-    split_slice_size = batch_size_attention
-    if block_size > 4:
-        do_split = True
-        #Find something divisible with the shape_one
-        while (split_slice_size * slice_block_size) > 4:
-            split_slice_size = split_slice_size // 2
-            if split_slice_size <= 1:
-                split_slice_size = 1
-                break
-    else:
-        do_split = False
-
-    split_2_slice_size = query_tokens
-    if split_slice_size * slice_block_size > 4:
-        slice_block_size2 = shape_one * split_slice_size * shape_four / 1024 / 1024 * block_multiply
-        do_split_2 = True
-        #Find something divisible with the batch_size_attention
-        while (split_2_slice_size * slice_block_size2) > 4:
-            split_2_slice_size = split_2_slice_size // 2
-            if split_2_slice_size <= 1:
-                split_2_slice_size = 1
-                break
-    else:
-        do_split_2 = False
+def scaled_dot_product_attention_32_bit(query, key, value, attn_mask=None, dropout_p=0.0, is_causal=False, **kwargs):
+    if query.device.type != "xpu":
+        return original_scaled_dot_product_attention(query, key, value, attn_mask=attn_mask, dropout_p=dropout_p, is_causal=is_causal, **kwargs)
+    do_split, do_split_2, do_split_3, split_slice_size, split_2_slice_size, split_3_slice_size = find_sdpa_slice_sizes(query.shape, query.element_size())
 
+    # Slice SDPA
     if do_split:
+        batch_size_attention, query_tokens, shape_three = query.shape[0], query.shape[1], query.shape[2]
         hidden_states = torch.zeros(query.shape, device=query.device, dtype=query.dtype)
         for i in range(batch_size_attention // split_slice_size):
             start_idx = i * split_slice_size
@@ -112,46 +144,34 @@ def scaled_dot_product_attention(query, key, value, attn_mask=None, dropout_p=0.
                 for i2 in range(query_tokens // split_2_slice_size): # pylint: disable=invalid-name
                     start_idx_2 = i2 * split_2_slice_size
                     end_idx_2 = (i2 + 1) * split_2_slice_size
-                    if no_shape_one:
+                    if do_split_3:
+                        for i3 in range(shape_three // split_3_slice_size): # pylint: disable=invalid-name
+                            start_idx_3 = i3 * split_3_slice_size
+                            end_idx_3 = (i3 + 1) * split_3_slice_size
+                            hidden_states[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3] = original_scaled_dot_product_attention(
+                                query[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3],
+                                key[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3],
+                                value[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3],
+                                attn_mask=attn_mask[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3] if attn_mask is not None else attn_mask,
+                                dropout_p=dropout_p, is_causal=is_causal, **kwargs
+                            )
+                    else:
                         hidden_states[start_idx:end_idx, start_idx_2:end_idx_2] = original_scaled_dot_product_attention(
                             query[start_idx:end_idx, start_idx_2:end_idx_2],
                             key[start_idx:end_idx, start_idx_2:end_idx_2],
                             value[start_idx:end_idx, start_idx_2:end_idx_2],
                             attn_mask=attn_mask[start_idx:end_idx, start_idx_2:end_idx_2] if attn_mask is not None else attn_mask,
-                            dropout_p=dropout_p, is_causal=is_causal
-                        )
-                    else:
-                        hidden_states[:, start_idx:end_idx, start_idx_2:end_idx_2] = original_scaled_dot_product_attention(
-                            query[:, start_idx:end_idx, start_idx_2:end_idx_2],
-                            key[:, start_idx:end_idx, start_idx_2:end_idx_2],
-                            value[:, start_idx:end_idx, start_idx_2:end_idx_2],
-                            attn_mask=attn_mask[:, start_idx:end_idx, start_idx_2:end_idx_2] if attn_mask is not None else attn_mask,
-                            dropout_p=dropout_p, is_causal=is_causal
+                            dropout_p=dropout_p, is_causal=is_causal, **kwargs
                         )
             else:
-                if no_shape_one:
-                    hidden_states[start_idx:end_idx] = original_scaled_dot_product_attention(
-                        query[start_idx:end_idx],
-                        key[start_idx:end_idx],
-                        value[start_idx:end_idx],
-                        attn_mask=attn_mask[start_idx:end_idx] if attn_mask is not None else attn_mask,
-                        dropout_p=dropout_p, is_causal=is_causal
-                    )
-                else:
-                    hidden_states[:, start_idx:end_idx] = original_scaled_dot_product_attention(
-                        query[:, start_idx:end_idx],
-                        key[:, start_idx:end_idx],
-                        value[:, start_idx:end_idx],
-                        attn_mask=attn_mask[:, start_idx:end_idx] if attn_mask is not None else attn_mask,
-                        dropout_p=dropout_p, is_causal=is_causal
-                    )
+                hidden_states[start_idx:end_idx] = original_scaled_dot_product_attention(
+                    query[start_idx:end_idx],
+                    key[start_idx:end_idx],
+                    value[start_idx:end_idx],
+                    attn_mask=attn_mask[start_idx:end_idx] if attn_mask is not None else attn_mask,
+                    dropout_p=dropout_p, is_causal=is_causal, **kwargs
+                )
+        torch.xpu.synchronize(query.device)
     else:
-        return original_scaled_dot_product_attention(
-            query, key, value, attn_mask=attn_mask, dropout_p=dropout_p, is_causal=is_causal
-        )
+        return original_scaled_dot_product_attention(query, key, value, attn_mask=attn_mask, dropout_p=dropout_p, is_causal=is_causal, **kwargs)
     return hidden_states
-
-def attention_init():
-    #ARC GPUs can't allocate more than 4GB to a single block:
-    torch.bmm = torch_bmm
-    torch.nn.functional.scaled_dot_product_attention = scaled_dot_product_attention

library/ipex/diffusers.py

@@ -1,10 +1,62 @@
+import os
 import torch
 import intel_extension_for_pytorch as ipex # pylint: disable=import-error, unused-import
-import diffusers #0.21.1 # pylint: disable=import-error
+import diffusers #0.24.0 # pylint: disable=import-error
 from diffusers.models.attention_processor import Attention
+from diffusers.utils import USE_PEFT_BACKEND
+from functools import cache
 
 # pylint: disable=protected-access, missing-function-docstring, line-too-long
 
+attention_slice_rate = float(os.environ.get('IPEX_ATTENTION_SLICE_RATE', 4))
+
+@cache
+def find_slice_size(slice_size, slice_block_size):
+    while (slice_size * slice_block_size) > attention_slice_rate:
+        slice_size = slice_size // 2
+        if slice_size <= 1:
+            slice_size = 1
+            break
+    return slice_size
+
+@cache
+def find_attention_slice_sizes(query_shape, query_element_size, query_device_type, slice_size=None):
+    if len(query_shape) == 3:
+        batch_size_attention, query_tokens, shape_three = query_shape
+        shape_four = 1
+    else:
+        batch_size_attention, query_tokens, shape_three, shape_four = query_shape
+    if slice_size is not None:
+        batch_size_attention = slice_size
+
+    slice_block_size = query_tokens * shape_three * shape_four / 1024 / 1024 * query_element_size
+    block_size = batch_size_attention * slice_block_size
+
+    split_slice_size = batch_size_attention
+    split_2_slice_size = query_tokens
+    split_3_slice_size = shape_three
+
+    do_split = False
+    do_split_2 = False
+    do_split_3 = False
+
+    if query_device_type != "xpu":
+        return do_split, do_split_2, do_split_3, split_slice_size, split_2_slice_size, split_3_slice_size
+
+    if block_size > attention_slice_rate:
+        do_split = True
+        split_slice_size = find_slice_size(split_slice_size, slice_block_size)
+        if split_slice_size * slice_block_size > attention_slice_rate:
+            slice_2_block_size = split_slice_size * shape_three * shape_four / 1024 / 1024 * query_element_size
+            do_split_2 = True
+            split_2_slice_size = find_slice_size(split_2_slice_size, slice_2_block_size)
+            if split_2_slice_size * slice_2_block_size > attention_slice_rate:
+                slice_3_block_size = split_slice_size * split_2_slice_size * shape_four / 1024 / 1024 * query_element_size
+                do_split_3 = True
+                split_3_slice_size = find_slice_size(split_3_slice_size, slice_3_block_size)
+
+    return do_split, do_split_2, do_split_3, split_slice_size, split_2_slice_size, split_3_slice_size
+
 class SlicedAttnProcessor: # pylint: disable=too-few-public-methods
     r"""
     Processor for implementing sliced attention.
@@ -18,7 +70,9 @@ class SlicedAttnProcessor: # pylint: disable=too-few-public-methods
     def __init__(self, slice_size):
         self.slice_size = slice_size
 
-    def __call__(self, attn: Attention, hidden_states, encoder_hidden_states=None, attention_mask=None): # pylint: disable=too-many-statements, too-many-locals, too-many-branches
+    def __call__(self, attn: Attention, hidden_states: torch.FloatTensor,
+    encoder_hidden_states=None, attention_mask=None) -> torch.FloatTensor: # pylint: disable=too-many-statements, too-many-locals, too-many-branches
+
         residual = hidden_states
 
         input_ndim = hidden_states.ndim
@@ -54,49 +108,62 @@ class SlicedAttnProcessor: # pylint: disable=too-few-public-methods
             (batch_size_attention, query_tokens, dim // attn.heads), device=query.device, dtype=query.dtype
         )
 
-        #ARC GPUs can't allocate more than 4GB to a single block, Slice it:
-        block_multiply = query.element_size()
-        slice_block_size = self.slice_size * shape_three / 1024 / 1024 * block_multiply
-        block_size = query_tokens * slice_block_size
-        split_2_slice_size = query_tokens
-        if block_size > 4:
-            do_split_2 = True
-            #Find something divisible with the query_tokens
-            while (split_2_slice_size * slice_block_size) > 4:
-                split_2_slice_size = split_2_slice_size // 2
-                if split_2_slice_size <= 1:
-                    split_2_slice_size = 1
-                    break
-        else:
-            do_split_2 = False
-
-        for i in range(batch_size_attention // self.slice_size):
-            start_idx = i * self.slice_size
-            end_idx = (i + 1) * self.slice_size
+        ####################################################################
+        # ARC GPUs can't allocate more than 4GB to a single block, Slice it:
+        _, do_split_2, do_split_3, split_slice_size, split_2_slice_size, split_3_slice_size = find_attention_slice_sizes(query.shape, query.element_size(), query.device.type, slice_size=self.slice_size)
 
+        for i in range(batch_size_attention // split_slice_size):
+            start_idx = i * split_slice_size
+            end_idx = (i + 1) * split_slice_size
             if do_split_2:
                 for i2 in range(query_tokens // split_2_slice_size): # pylint: disable=invalid-name
                     start_idx_2 = i2 * split_2_slice_size
                     end_idx_2 = (i2 + 1) * split_2_slice_size
+                    if do_split_3:
+                        for i3 in range(shape_three // split_3_slice_size): # pylint: disable=invalid-name
+                            start_idx_3 = i3 * split_3_slice_size
+                            end_idx_3 = (i3 + 1) * split_3_slice_size
 
-                    query_slice = query[start_idx:end_idx, start_idx_2:end_idx_2]
-                    key_slice = key[start_idx:end_idx, start_idx_2:end_idx_2]
-                    attn_mask_slice = attention_mask[start_idx:end_idx, start_idx_2:end_idx_2] if attention_mask is not None else None
+                            query_slice = query[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3]
+                            key_slice = key[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3]
+                            attn_mask_slice = attention_mask[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3] if attention_mask is not None else None
 
-                    attn_slice = attn.get_attention_scores(query_slice, key_slice, attn_mask_slice)
-                    attn_slice = torch.bmm(attn_slice, value[start_idx:end_idx, start_idx_2:end_idx_2])
+                            attn_slice = attn.get_attention_scores(query_slice, key_slice, attn_mask_slice)
+                            del query_slice
+                            del key_slice
+                            del attn_mask_slice
+                            attn_slice = torch.bmm(attn_slice, value[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3])
 
-                    hidden_states[start_idx:end_idx, start_idx_2:end_idx_2] = attn_slice
+                            hidden_states[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3] = attn_slice
+                            del attn_slice
+                    else:
+                        query_slice = query[start_idx:end_idx, start_idx_2:end_idx_2]
+                        key_slice = key[start_idx:end_idx, start_idx_2:end_idx_2]
+                        attn_mask_slice = attention_mask[start_idx:end_idx, start_idx_2:end_idx_2] if attention_mask is not None else None
+
+                        attn_slice = attn.get_attention_scores(query_slice, key_slice, attn_mask_slice)
+                        del query_slice
+                        del key_slice
+                        del attn_mask_slice
+                        attn_slice = torch.bmm(attn_slice, value[start_idx:end_idx, start_idx_2:end_idx_2])
+
+                        hidden_states[start_idx:end_idx, start_idx_2:end_idx_2] = attn_slice
+                        del attn_slice
+                torch.xpu.synchronize(query.device)
             else:
                 query_slice = query[start_idx:end_idx]
                 key_slice = key[start_idx:end_idx]
                 attn_mask_slice = attention_mask[start_idx:end_idx] if attention_mask is not None else None
 
                 attn_slice = attn.get_attention_scores(query_slice, key_slice, attn_mask_slice)
-
+                del query_slice
+                del key_slice
+                del attn_mask_slice
                 attn_slice = torch.bmm(attn_slice, value[start_idx:end_idx])
 
                 hidden_states[start_idx:end_idx] = attn_slice
+                del attn_slice
+        ####################################################################
 
         hidden_states = attn.batch_to_head_dim(hidden_states)
 
@@ -115,6 +182,131 @@ class SlicedAttnProcessor: # pylint: disable=too-few-public-methods
 
         return hidden_states
 
+
+class AttnProcessor:
+    r"""
+    Default processor for performing attention-related computations.
+    """
+
+    def __call__(self, attn: Attention, hidden_states: torch.FloatTensor,
+    encoder_hidden_states=None, attention_mask=None,
+    temb=None, scale: float = 1.0) -> torch.Tensor: # pylint: disable=too-many-statements, too-many-locals, too-many-branches
+
+        residual = hidden_states
+
+        args = () if USE_PEFT_BACKEND else (scale,)
+
+        if attn.spatial_norm is not None:
+            hidden_states = attn.spatial_norm(hidden_states, temb)
+
+        input_ndim = hidden_states.ndim
+
+        if input_ndim == 4:
+            batch_size, channel, height, width = hidden_states.shape
+            hidden_states = hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
+
+        batch_size, sequence_length, _ = (
+            hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
+        )
+        attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length, batch_size)
+
+        if attn.group_norm is not None:
+            hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
+
+        query = attn.to_q(hidden_states, *args)
+
+        if encoder_hidden_states is None:
+            encoder_hidden_states = hidden_states
+        elif attn.norm_cross:
+            encoder_hidden_states = attn.norm_encoder_hidden_states(encoder_hidden_states)
+
+        key = attn.to_k(encoder_hidden_states, *args)
+        value = attn.to_v(encoder_hidden_states, *args)
+
+        query = attn.head_to_batch_dim(query)
+        key = attn.head_to_batch_dim(key)
+        value = attn.head_to_batch_dim(value)
+
+        ####################################################################
+        # ARC GPUs can't allocate more than 4GB to a single block, Slice it:
+        batch_size_attention, query_tokens, shape_three = query.shape[0], query.shape[1], query.shape[2]
+        hidden_states = torch.zeros(query.shape, device=query.device, dtype=query.dtype)
+        do_split, do_split_2, do_split_3, split_slice_size, split_2_slice_size, split_3_slice_size = find_attention_slice_sizes(query.shape, query.element_size(), query.device.type)
+
+        if do_split:
+            for i in range(batch_size_attention // split_slice_size):
+                start_idx = i * split_slice_size
+                end_idx = (i + 1) * split_slice_size
+                if do_split_2:
+                    for i2 in range(query_tokens // split_2_slice_size): # pylint: disable=invalid-name
+                        start_idx_2 = i2 * split_2_slice_size
+                        end_idx_2 = (i2 + 1) * split_2_slice_size
+                        if do_split_3:
+                            for i3 in range(shape_three // split_3_slice_size): # pylint: disable=invalid-name
+                                start_idx_3 = i3 * split_3_slice_size
+                                end_idx_3 = (i3 + 1) * split_3_slice_size
+
+                                query_slice = query[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3]
+                                key_slice = key[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3]
+                                attn_mask_slice = attention_mask[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3] if attention_mask is not None else None
+
+                                attn_slice = attn.get_attention_scores(query_slice, key_slice, attn_mask_slice)
+                                del query_slice
+                                del key_slice
+                                del attn_mask_slice
+                                attn_slice = torch.bmm(attn_slice, value[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3])
+
+                                hidden_states[start_idx:end_idx, start_idx_2:end_idx_2, start_idx_3:end_idx_3] = attn_slice
+                                del attn_slice
+                        else:
+                            query_slice = query[start_idx:end_idx, start_idx_2:end_idx_2]
+                            key_slice = key[start_idx:end_idx, start_idx_2:end_idx_2]
+                            attn_mask_slice = attention_mask[start_idx:end_idx, start_idx_2:end_idx_2] if attention_mask is not None else None
+
+                            attn_slice = attn.get_attention_scores(query_slice, key_slice, attn_mask_slice)
+                            del query_slice
+                            del key_slice
+                            del attn_mask_slice
+                            attn_slice = torch.bmm(attn_slice, value[start_idx:end_idx, start_idx_2:end_idx_2])
+
+                            hidden_states[start_idx:end_idx, start_idx_2:end_idx_2] = attn_slice
+                            del attn_slice
+                else:
+                    query_slice = query[start_idx:end_idx]
+                    key_slice = key[start_idx:end_idx]
+                    attn_mask_slice = attention_mask[start_idx:end_idx] if attention_mask is not None else None
+
+                    attn_slice = attn.get_attention_scores(query_slice, key_slice, attn_mask_slice)
+                    del query_slice
+                    del key_slice
+                    del attn_mask_slice
+                    attn_slice = torch.bmm(attn_slice, value[start_idx:end_idx])
+
+                    hidden_states[start_idx:end_idx] = attn_slice
+                    del attn_slice
+            torch.xpu.synchronize(query.device)
+        else:
+            attention_probs = attn.get_attention_scores(query, key, attention_mask)
+            hidden_states = torch.bmm(attention_probs, value)
+        ####################################################################
+        hidden_states = attn.batch_to_head_dim(hidden_states)
+
+        # linear proj
+        hidden_states = attn.to_out[0](hidden_states, *args)
+        # dropout
+        hidden_states = attn.to_out[1](hidden_states)
+
+        if input_ndim == 4:
+            hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
+
+        if attn.residual_connection:
+            hidden_states = hidden_states + residual
+
+        hidden_states = hidden_states / attn.rescale_output_factor
+
+        return hidden_states
+
 def ipex_diffusers():
     #ARC GPUs can't allocate more than 4GB to a single block:
     diffusers.models.attention_processor.SlicedAttnProcessor = SlicedAttnProcessor
+    diffusers.models.attention_processor.AttnProcessor = AttnProcessor

library/ipex/gradscaler.py

@@ -5,6 +5,7 @@ import intel_extension_for_pytorch._C as core # pylint: disable=import-error, un
 
 # pylint: disable=protected-access, missing-function-docstring, line-too-long
 
+device_supports_fp64 = torch.xpu.has_fp64_dtype()
 OptState = ipex.cpu.autocast._grad_scaler.OptState
 _MultiDeviceReplicator = ipex.cpu.autocast._grad_scaler._MultiDeviceReplicator
 _refresh_per_optimizer_state = ipex.cpu.autocast._grad_scaler._refresh_per_optimizer_state
@@ -96,7 +97,10 @@ def unscale_(self, optimizer):
 
     # FP32 division can be imprecise for certain compile options, so we carry out the reciprocal in FP64.
     assert self._scale is not None
-    inv_scale = self._scale.to("cpu").double().reciprocal().float().to(self._scale.device)
+    if device_supports_fp64:
+        inv_scale = self._scale.double().reciprocal().float()
+    else:
+        inv_scale = self._scale.to("cpu").double().reciprocal().float().to(self._scale.device)
     found_inf = torch.full(
         (1,), 0.0, dtype=torch.float32, device=self._scale.device
     )

library/ipex/hijacks.py

@@ -1,67 +1,14 @@
-import contextlib
-import importlib
+import os
+from functools import wraps
+from contextlib import nullcontext
 import torch
 import intel_extension_for_pytorch as ipex # pylint: disable=import-error, unused-import
+import numpy as np
+
+device_supports_fp64 = torch.xpu.has_fp64_dtype()
 
 # pylint: disable=protected-access, missing-function-docstring, line-too-long, unnecessary-lambda, no-else-return
 
-class CondFunc: # pylint: disable=missing-class-docstring
-    def __new__(cls, orig_func, sub_func, cond_func):
-        self = super(CondFunc, cls).__new__(cls)
-        if isinstance(orig_func, str):
-            func_path = orig_func.split('.')
-            for i in range(len(func_path)-1, -1, -1):
-                try:
-                    resolved_obj = importlib.import_module('.'.join(func_path[:i]))
-                    break
-                except ImportError:
-                    pass
-            for attr_name in func_path[i:-1]:
-                resolved_obj = getattr(resolved_obj, attr_name)
-            orig_func = getattr(resolved_obj, func_path[-1])
-            setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
-        self.__init__(orig_func, sub_func, cond_func)
-        return lambda *args, **kwargs: self(*args, **kwargs)
-    def __init__(self, orig_func, sub_func, cond_func):
-        self.__orig_func = orig_func
-        self.__sub_func = sub_func
-        self.__cond_func = cond_func
-    def __call__(self, *args, **kwargs):
-        if not self.__cond_func or self.__cond_func(self.__orig_func, *args, **kwargs):
-            return self.__sub_func(self.__orig_func, *args, **kwargs)
-        else:
-            return self.__orig_func(*args, **kwargs)
-
-_utils = torch.utils.data._utils
-def _shutdown_workers(self):
-    if torch.utils.data._utils is None or torch.utils.data._utils.python_exit_status is True or torch.utils.data._utils.python_exit_status is None:
-        return
-    if hasattr(self, "_shutdown") and not self._shutdown:
-        self._shutdown = True
-        try:
-            if hasattr(self, '_pin_memory_thread'):
-                self._pin_memory_thread_done_event.set()
-                self._worker_result_queue.put((None, None))
-                self._pin_memory_thread.join()
-                self._worker_result_queue.cancel_join_thread()
-                self._worker_result_queue.close()
-            self._workers_done_event.set()
-            for worker_id in range(len(self._workers)):
-                if self._persistent_workers or self._workers_status[worker_id]:
-                    self._mark_worker_as_unavailable(worker_id, shutdown=True)
-            for w in self._workers: # pylint: disable=invalid-name
-                w.join(timeout=torch.utils.data._utils.MP_STATUS_CHECK_INTERVAL)
-            for q in self._index_queues: # pylint: disable=invalid-name
-                q.cancel_join_thread()
-                q.close()
-        finally:
-            if self._worker_pids_set:
-                torch.utils.data._utils.signal_handling._remove_worker_pids(id(self))
-                self._worker_pids_set = False
-            for w in self._workers: # pylint: disable=invalid-name
-                if w.is_alive():
-                    w.terminate()
-
 class DummyDataParallel(torch.nn.Module): # pylint: disable=missing-class-docstring, unused-argument, too-few-public-methods
     def __new__(cls, module, device_ids=None, output_device=None, dim=0): # pylint: disable=unused-argument
         if isinstance(device_ids, list) and len(device_ids) > 1:
@@ -69,7 +16,11 @@ class DummyDataParallel(torch.nn.Module): # pylint: disable=missing-class-docstr
         return module.to("xpu")
 
 def return_null_context(*args, **kwargs): # pylint: disable=unused-argument
-    return contextlib.nullcontext()
+    return nullcontext()
+
+@property
+def is_cuda(self):
+    return self.device.type == 'xpu' or self.device.type == 'cuda'
 
 def check_device(device):
     return bool((isinstance(device, torch.device) and device.type == "cuda") or (isinstance(device, str) and "cuda" in device) or isinstance(device, int))
@@ -77,28 +28,21 @@ def check_device(device):
 def return_xpu(device):
     return f"xpu:{device.split(':')[-1]}" if isinstance(device, str) and ":" in device else f"xpu:{device}" if isinstance(device, int) else torch.device("xpu") if isinstance(device, torch.device) else "xpu"
 
-def ipex_no_cuda(orig_func, *args, **kwargs):
-    torch.cuda.is_available = lambda: False
-    orig_func(*args, **kwargs)
-    torch.cuda.is_available = torch.xpu.is_available
 
-original_autocast = torch.autocast
-def ipex_autocast(*args, **kwargs):
-    if len(args) > 0 and args[0] == "cuda":
-        return original_autocast("xpu", *args[1:], **kwargs)
+# Autocast
+original_autocast_init = torch.amp.autocast_mode.autocast.__init__
+@wraps(torch.amp.autocast_mode.autocast.__init__)
+def autocast_init(self, device_type, dtype=None, enabled=True, cache_enabled=None):
+    if device_type == "cuda":
+        return original_autocast_init(self, device_type="xpu", dtype=dtype, enabled=enabled, cache_enabled=cache_enabled)
     else:
-        return original_autocast(*args, **kwargs)
-
-original_torch_cat = torch.cat
-def torch_cat(tensor, *args, **kwargs):
-    if len(tensor) == 3 and (tensor[0].dtype != tensor[1].dtype or tensor[2].dtype != tensor[1].dtype):
-        return original_torch_cat([tensor[0].to(tensor[1].dtype), tensor[1], tensor[2].to(tensor[1].dtype)], *args, **kwargs)
-    else:
-        return original_torch_cat(tensor, *args, **kwargs)
+        return original_autocast_init(self, device_type=device_type, dtype=dtype, enabled=enabled, cache_enabled=cache_enabled)
 
+# Latent Antialias CPU Offload:
 original_interpolate = torch.nn.functional.interpolate
+@wraps(torch.nn.functional.interpolate)
 def interpolate(tensor, size=None, scale_factor=None, mode='nearest', align_corners=None, recompute_scale_factor=None, antialias=False): # pylint: disable=too-many-arguments
-    if antialias or align_corners is not None:
+    if antialias or align_corners is not None or mode == 'bicubic':
         return_device = tensor.device
         return_dtype = tensor.dtype
         return original_interpolate(tensor.to("cpu", dtype=torch.float32), size=size, scale_factor=scale_factor, mode=mode,
@@ -107,90 +51,263 @@ def interpolate(tensor, size=None, scale_factor=None, mode='nearest', align_corn
         return original_interpolate(tensor, size=size, scale_factor=scale_factor, mode=mode,
         align_corners=align_corners, recompute_scale_factor=recompute_scale_factor, antialias=antialias)
 
-original_linalg_solve = torch.linalg.solve
-def linalg_solve(A, B, *args, **kwargs): # pylint: disable=invalid-name
-    if A.device != torch.device("cpu") or B.device != torch.device("cpu"):
-        return_device = A.device
-        return original_linalg_solve(A.to("cpu"), B.to("cpu"), *args, **kwargs).to(return_device)
+
+# Diffusers Float64 (Alchemist GPUs doesn't support 64 bit):
+original_from_numpy = torch.from_numpy
+@wraps(torch.from_numpy)
+def from_numpy(ndarray):
+    if ndarray.dtype == float:
+        return original_from_numpy(ndarray.astype('float32'))
     else:
-        return original_linalg_solve(A, B, *args, **kwargs)
+        return original_from_numpy(ndarray)
 
+original_as_tensor = torch.as_tensor
+@wraps(torch.as_tensor)
+def as_tensor(data, dtype=None, device=None):
+    if check_device(device):
+        device = return_xpu(device)
+    if isinstance(data, np.ndarray) and data.dtype == float and not (
+        (isinstance(device, torch.device) and device.type == "cpu") or (isinstance(device, str) and "cpu" in device)):
+        return original_as_tensor(data, dtype=torch.float32, device=device)
+    else:
+        return original_as_tensor(data, dtype=dtype, device=device)
+
+
+if device_supports_fp64 and os.environ.get('IPEX_FORCE_ATTENTION_SLICE', None) is None:
+    original_torch_bmm = torch.bmm
+    original_scaled_dot_product_attention = torch.nn.functional.scaled_dot_product_attention
+else:
+    # 32 bit attention workarounds for Alchemist:
+    try:
+        from .attention import torch_bmm_32_bit as original_torch_bmm
+        from .attention import scaled_dot_product_attention_32_bit as original_scaled_dot_product_attention
+    except Exception: # pylint: disable=broad-exception-caught
+        original_torch_bmm = torch.bmm
+        original_scaled_dot_product_attention = torch.nn.functional.scaled_dot_product_attention
+
+
+# Data Type Errors:
+@wraps(torch.bmm)
+def torch_bmm(input, mat2, *, out=None):
+    if input.dtype != mat2.dtype:
+        mat2 = mat2.to(input.dtype)
+    return original_torch_bmm(input, mat2, out=out)
+
+@wraps(torch.nn.functional.scaled_dot_product_attention)
+def scaled_dot_product_attention(query, key, value, attn_mask=None, dropout_p=0.0, is_causal=False):
+    if query.dtype != key.dtype:
+        key = key.to(dtype=query.dtype)
+    if query.dtype != value.dtype:
+        value = value.to(dtype=query.dtype)
+    if attn_mask is not None and query.dtype != attn_mask.dtype:
+        attn_mask = attn_mask.to(dtype=query.dtype)
+    return original_scaled_dot_product_attention(query, key, value, attn_mask=attn_mask, dropout_p=dropout_p, is_causal=is_causal)
+
+# A1111 FP16
+original_functional_group_norm = torch.nn.functional.group_norm
+@wraps(torch.nn.functional.group_norm)
+def functional_group_norm(input, num_groups, weight=None, bias=None, eps=1e-05):
+    if weight is not None and input.dtype != weight.data.dtype:
+        input = input.to(dtype=weight.data.dtype)
+    if bias is not None and weight is not None and bias.data.dtype != weight.data.dtype:
+        bias.data = bias.data.to(dtype=weight.data.dtype)
+    return original_functional_group_norm(input, num_groups, weight=weight, bias=bias, eps=eps)
+
+# A1111 BF16
+original_functional_layer_norm = torch.nn.functional.layer_norm
+@wraps(torch.nn.functional.layer_norm)
+def functional_layer_norm(input, normalized_shape, weight=None, bias=None, eps=1e-05):
+    if weight is not None and input.dtype != weight.data.dtype:
+        input = input.to(dtype=weight.data.dtype)
+    if bias is not None and weight is not None and bias.data.dtype != weight.data.dtype:
+        bias.data = bias.data.to(dtype=weight.data.dtype)
+    return original_functional_layer_norm(input, normalized_shape, weight=weight, bias=bias, eps=eps)
+
+# Training
+original_functional_linear = torch.nn.functional.linear
+@wraps(torch.nn.functional.linear)
+def functional_linear(input, weight, bias=None):
+    if input.dtype != weight.data.dtype:
+        input = input.to(dtype=weight.data.dtype)
+    if bias is not None and bias.data.dtype != weight.data.dtype:
+        bias.data = bias.data.to(dtype=weight.data.dtype)
+    return original_functional_linear(input, weight, bias=bias)
+
+original_functional_conv2d = torch.nn.functional.conv2d
+@wraps(torch.nn.functional.conv2d)
+def functional_conv2d(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1):
+    if input.dtype != weight.data.dtype:
+        input = input.to(dtype=weight.data.dtype)
+    if bias is not None and bias.data.dtype != weight.data.dtype:
+        bias.data = bias.data.to(dtype=weight.data.dtype)
+    return original_functional_conv2d(input, weight, bias=bias, stride=stride, padding=padding, dilation=dilation, groups=groups)
+
+# A1111 Embedding BF16
+original_torch_cat = torch.cat
+@wraps(torch.cat)
+def torch_cat(tensor, *args, **kwargs):
+    if len(tensor) == 3 and (tensor[0].dtype != tensor[1].dtype or tensor[2].dtype != tensor[1].dtype):
+        return original_torch_cat([tensor[0].to(tensor[1].dtype), tensor[1], tensor[2].to(tensor[1].dtype)], *args, **kwargs)
+    else:
+        return original_torch_cat(tensor, *args, **kwargs)
+
+# SwinIR BF16:
+original_functional_pad = torch.nn.functional.pad
+@wraps(torch.nn.functional.pad)
+def functional_pad(input, pad, mode='constant', value=None):
+    if mode == 'reflect' and input.dtype == torch.bfloat16:
+        return original_functional_pad(input.to(torch.float32), pad, mode=mode, value=value).to(dtype=torch.bfloat16)
+    else:
+        return original_functional_pad(input, pad, mode=mode, value=value)
+
+
+original_torch_tensor = torch.tensor
+@wraps(torch.tensor)
+def torch_tensor(data, *args, dtype=None, device=None, **kwargs):
+    if check_device(device):
+        device = return_xpu(device)
+    if not device_supports_fp64:
+        if (isinstance(device, torch.device) and device.type == "xpu") or (isinstance(device, str) and "xpu" in device):
+            if dtype == torch.float64:
+                dtype = torch.float32
+            elif dtype is None and (hasattr(data, "dtype") and (data.dtype == torch.float64 or data.dtype == float)):
+                dtype = torch.float32
+    return original_torch_tensor(data, *args, dtype=dtype, device=device, **kwargs)
+
+original_Tensor_to = torch.Tensor.to
+@wraps(torch.Tensor.to)
+def Tensor_to(self, device=None, *args, **kwargs):
+    if check_device(device):
+        return original_Tensor_to(self, return_xpu(device), *args, **kwargs)
+    else:
+        return original_Tensor_to(self, device, *args, **kwargs)
+
+original_Tensor_cuda = torch.Tensor.cuda
+@wraps(torch.Tensor.cuda)
+def Tensor_cuda(self, device=None, *args, **kwargs):
+    if check_device(device):
+        return original_Tensor_cuda(self, return_xpu(device), *args, **kwargs)
+    else:
+        return original_Tensor_cuda(self, device, *args, **kwargs)
+
+original_Tensor_pin_memory = torch.Tensor.pin_memory
+@wraps(torch.Tensor.pin_memory)
+def Tensor_pin_memory(self, device=None, *args, **kwargs):
+    if device is None:
+        device = "xpu"
+    if check_device(device):
+        return original_Tensor_pin_memory(self, return_xpu(device), *args, **kwargs)
+    else:
+        return original_Tensor_pin_memory(self, device, *args, **kwargs)
+
+original_UntypedStorage_init = torch.UntypedStorage.__init__
+@wraps(torch.UntypedStorage.__init__)
+def UntypedStorage_init(*args, device=None, **kwargs):
+    if check_device(device):
+        return original_UntypedStorage_init(*args, device=return_xpu(device), **kwargs)
+    else:
+        return original_UntypedStorage_init(*args, device=device, **kwargs)
+
+original_UntypedStorage_cuda = torch.UntypedStorage.cuda
+@wraps(torch.UntypedStorage.cuda)
+def UntypedStorage_cuda(self, device=None, *args, **kwargs):
+    if check_device(device):
+        return original_UntypedStorage_cuda(self, return_xpu(device), *args, **kwargs)
+    else:
+        return original_UntypedStorage_cuda(self, device, *args, **kwargs)
+
+original_torch_empty = torch.empty
+@wraps(torch.empty)
+def torch_empty(*args, device=None, **kwargs):
+    if check_device(device):
+        return original_torch_empty(*args, device=return_xpu(device), **kwargs)
+    else:
+        return original_torch_empty(*args, device=device, **kwargs)
+
+original_torch_randn = torch.randn
+@wraps(torch.randn)
+def torch_randn(*args, device=None, dtype=None, **kwargs):
+    if dtype == bytes:
+        dtype = None
+    if check_device(device):
+        return original_torch_randn(*args, device=return_xpu(device), **kwargs)
+    else:
+        return original_torch_randn(*args, device=device, **kwargs)
+
+original_torch_ones = torch.ones
+@wraps(torch.ones)
+def torch_ones(*args, device=None, **kwargs):
+    if check_device(device):
+        return original_torch_ones(*args, device=return_xpu(device), **kwargs)
+    else:
+        return original_torch_ones(*args, device=device, **kwargs)
+
+original_torch_zeros = torch.zeros
+@wraps(torch.zeros)
+def torch_zeros(*args, device=None, **kwargs):
+    if check_device(device):
+        return original_torch_zeros(*args, device=return_xpu(device), **kwargs)
+    else:
+        return original_torch_zeros(*args, device=device, **kwargs)
+
+original_torch_linspace = torch.linspace
+@wraps(torch.linspace)
+def torch_linspace(*args, device=None, **kwargs):
+    if check_device(device):
+        return original_torch_linspace(*args, device=return_xpu(device), **kwargs)
+    else:
+        return original_torch_linspace(*args, device=device, **kwargs)
+
+original_torch_Generator = torch.Generator
+@wraps(torch.Generator)
+def torch_Generator(device=None):
+    if check_device(device):
+        return original_torch_Generator(return_xpu(device))
+    else:
+        return original_torch_Generator(device)
+
+original_torch_load = torch.load
+@wraps(torch.load)
+def torch_load(f, map_location=None, *args, **kwargs):
+    if map_location is None:
+        map_location = "xpu"
+    if check_device(map_location):
+        return original_torch_load(f, *args, map_location=return_xpu(map_location), **kwargs)
+    else:
+        return original_torch_load(f, *args, map_location=map_location, **kwargs)
+
+
+# Hijack Functions:
 def ipex_hijacks():
-    CondFunc('torch.Tensor.to',
-        lambda orig_func, self, device=None, *args, **kwargs: orig_func(self, return_xpu(device), *args, **kwargs),
-        lambda orig_func, self, device=None, *args, **kwargs: check_device(device))
-    CondFunc('torch.Tensor.cuda',
-        lambda orig_func, self, device=None, *args, **kwargs: orig_func(self, return_xpu(device), *args, **kwargs),
-        lambda orig_func, self, device=None, *args, **kwargs: check_device(device))
-    CondFunc('torch.empty',
-        lambda orig_func, *args, device=None, **kwargs: orig_func(*args, device=return_xpu(device), **kwargs),
-        lambda orig_func, *args, device=None, **kwargs: check_device(device))
-    CondFunc('torch.load',
-        lambda orig_func, *args, map_location=None, **kwargs: orig_func(*args, return_xpu(map_location), **kwargs),
-        lambda orig_func, *args, map_location=None, **kwargs: map_location is None or check_device(map_location))
-    CondFunc('torch.randn',
-        lambda orig_func, *args, device=None, **kwargs: orig_func(*args, device=return_xpu(device), **kwargs),
-        lambda orig_func, *args, device=None, **kwargs: check_device(device))
-    CondFunc('torch.ones',
-        lambda orig_func, *args, device=None, **kwargs: orig_func(*args, device=return_xpu(device), **kwargs),
-        lambda orig_func, *args, device=None, **kwargs: check_device(device))
-    CondFunc('torch.zeros',
-        lambda orig_func, *args, device=None, **kwargs: orig_func(*args, device=return_xpu(device), **kwargs),
-        lambda orig_func, *args, device=None, **kwargs: check_device(device))
-    CondFunc('torch.tensor',
-        lambda orig_func, *args, device=None, **kwargs: orig_func(*args, device=return_xpu(device), **kwargs),
-        lambda orig_func, *args, device=None, **kwargs: check_device(device))
-    CondFunc('torch.linspace',
-        lambda orig_func, *args, device=None, **kwargs: orig_func(*args, device=return_xpu(device), **kwargs),
-        lambda orig_func, *args, device=None, **kwargs: check_device(device))
+    torch.tensor = torch_tensor
+    torch.Tensor.to = Tensor_to
+    torch.Tensor.cuda = Tensor_cuda
+    torch.Tensor.pin_memory = Tensor_pin_memory
+    torch.UntypedStorage.__init__ = UntypedStorage_init
+    torch.UntypedStorage.cuda = UntypedStorage_cuda
+    torch.empty = torch_empty
+    torch.randn = torch_randn
+    torch.ones = torch_ones
+    torch.zeros = torch_zeros
+    torch.linspace = torch_linspace
+    torch.Generator = torch_Generator
+    torch.load = torch_load
 
-    CondFunc('torch.Generator',
-        lambda orig_func, device=None: torch.xpu.Generator(device),
-        lambda orig_func, device=None: device is not None and device != torch.device("cpu") and device != "cpu")
-
-    CondFunc('torch.batch_norm',
-        lambda orig_func, input, weight, bias, *args, **kwargs: orig_func(input,
-        weight if weight is not None else torch.ones(input.size()[1], device=input.device),
-        bias if bias is not None else torch.zeros(input.size()[1], device=input.device), *args, **kwargs),
-        lambda orig_func, input, *args, **kwargs: input.device != torch.device("cpu"))
-    CondFunc('torch.instance_norm',
-        lambda orig_func, input, weight, bias, *args, **kwargs: orig_func(input,
-        weight if weight is not None else torch.ones(input.size()[1], device=input.device),
-        bias if bias is not None else torch.zeros(input.size()[1], device=input.device), *args, **kwargs),
-        lambda orig_func, input, *args, **kwargs: input.device != torch.device("cpu"))
-
-    #Functions with dtype errors:
-    CondFunc('torch.nn.modules.GroupNorm.forward',
-        lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
-        lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
-    CondFunc('torch.nn.modules.linear.Linear.forward',
-        lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
-        lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
-    CondFunc('torch.nn.modules.conv.Conv2d.forward',
-        lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
-        lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
-    CondFunc('torch.nn.functional.layer_norm',
-        lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs:
-        orig_func(input.to(weight.data.dtype), normalized_shape, weight, *args, **kwargs),
-        lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs:
-        weight is not None and input.dtype != weight.data.dtype)
-
-    #Diffusers Float64 (ARC GPUs doesn't support double or Float64):
-    if not torch.xpu.has_fp64_dtype():
-        CondFunc('torch.from_numpy',
-        lambda orig_func, ndarray: orig_func(ndarray.astype('float32')),
-        lambda orig_func, ndarray: ndarray.dtype == float)
-
-    #Broken functions when torch.cuda.is_available is True:
-    CondFunc('torch.utils.data.dataloader._BaseDataLoaderIter.__init__',
-        lambda orig_func, *args, **kwargs: ipex_no_cuda(orig_func, *args, **kwargs),
-        lambda orig_func, *args, **kwargs: True)
-
-    #Functions that make compile mad with CondFunc:
-    torch.utils.data.dataloader._MultiProcessingDataLoaderIter._shutdown_workers = _shutdown_workers
-    torch.nn.DataParallel = DummyDataParallel
-    torch.autocast = ipex_autocast
-    torch.cat = torch_cat
-    torch.linalg.solve = linalg_solve
-    torch.nn.functional.interpolate = interpolate
     torch.backends.cuda.sdp_kernel = return_null_context
+    torch.nn.DataParallel = DummyDataParallel
+    torch.UntypedStorage.is_cuda = is_cuda
+    torch.amp.autocast_mode.autocast.__init__ = autocast_init
+
+    torch.nn.functional.scaled_dot_product_attention = scaled_dot_product_attention
+    torch.nn.functional.group_norm = functional_group_norm
+    torch.nn.functional.layer_norm = functional_layer_norm
+    torch.nn.functional.linear = functional_linear
+    torch.nn.functional.conv2d = functional_conv2d
+    torch.nn.functional.interpolate = interpolate
+    torch.nn.functional.pad = functional_pad
+
+    torch.bmm = torch_bmm
+    torch.cat = torch_cat
+    if not device_supports_fp64:
+        torch.from_numpy = from_numpy
+        torch.as_tensor = as_tensor

library/lpw_stable_diffusion.py

@@ -9,7 +9,7 @@ import numpy as np
 import PIL.Image
 import torch
 from packaging import version
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
 import diffusers
 from diffusers import SchedulerMixin, StableDiffusionPipeline
@@ -17,7 +17,6 @@ from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput, StableDiffusionSafetyChecker
 from diffusers.utils import logging
 
-
 try:
     from diffusers.utils import PIL_INTERPOLATION
 except ImportError:
@@ -520,6 +519,7 @@ class StableDiffusionLongPromptWeightingPipeline(StableDiffusionPipeline):
         safety_checker: StableDiffusionSafetyChecker,
         feature_extractor: CLIPFeatureExtractor,
         requires_safety_checker: bool = True,
+        image_encoder: CLIPVisionModelWithProjection = None,
         clip_skip: int = 1,
     ):
         super().__init__(
@@ -531,32 +531,11 @@ class StableDiffusionLongPromptWeightingPipeline(StableDiffusionPipeline):
             safety_checker=safety_checker,
             feature_extractor=feature_extractor,
             requires_safety_checker=requires_safety_checker,
+            image_encoder=image_encoder,
         )
-        self.clip_skip = clip_skip
+        self.custom_clip_skip = clip_skip
         self.__init__additional__()
 
-    # else:
-    #     def __init__(
-    #         self,
-    #         vae: AutoencoderKL,
-    #         text_encoder: CLIPTextModel,
-    #         tokenizer: CLIPTokenizer,
-    #         unet: UNet2DConditionModel,
-    #         scheduler: SchedulerMixin,
-    #         safety_checker: StableDiffusionSafetyChecker,
-    #         feature_extractor: CLIPFeatureExtractor,
-    #     ):
-    #         super().__init__(
-    #             vae=vae,
-    #             text_encoder=text_encoder,
-    #             tokenizer=tokenizer,
-    #             unet=unet,
-    #             scheduler=scheduler,
-    #             safety_checker=safety_checker,
-    #             feature_extractor=feature_extractor,
-    #         )
-    #         self.__init__additional__()
-
     def __init__additional__(self):
         if not hasattr(self, "vae_scale_factor"):
             setattr(self, "vae_scale_factor", 2 ** (len(self.vae.config.block_out_channels) - 1))
@@ -624,7 +603,7 @@ class StableDiffusionLongPromptWeightingPipeline(StableDiffusionPipeline):
             prompt=prompt,
             uncond_prompt=negative_prompt if do_classifier_free_guidance else None,
             max_embeddings_multiples=max_embeddings_multiples,
-            clip_skip=self.clip_skip,
+            clip_skip=self.custom_clip_skip,
         )
         bs_embed, seq_len, _ = text_embeddings.shape
         text_embeddings = text_embeddings.repeat(1, num_images_per_prompt, 1)
@@ -646,7 +625,7 @@ class StableDiffusionLongPromptWeightingPipeline(StableDiffusionPipeline):
             raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
 
         if height % 8 != 0 or width % 8 != 0:
-            print(height, width)
+            logger.info(f'{height} {width}')
             raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
 
         if (callback_steps is None) or (

library/model_util.py

@@ -3,19 +3,20 @@
 
 import math
 import os
+
 import torch
-try:
-    import intel_extension_for_pytorch as ipex
-    if torch.xpu.is_available():
-        from library.ipex import ipex_init
-        ipex_init()
-except Exception:
-    pass
+from library.device_utils import init_ipex
+init_ipex()
+
 import diffusers
 from transformers import CLIPTextModel, CLIPTokenizer, CLIPTextConfig, logging
 from diffusers import AutoencoderKL, DDIMScheduler, StableDiffusionPipeline  # , UNet2DConditionModel
 from safetensors.torch import load_file, save_file
 from library.original_unet import UNet2DConditionModel
+from library.utils import setup_logging
+setup_logging()
+import logging
+logger = logging.getLogger(__name__)
 
 # DiffUsers版StableDiffusionのモデルパラメータ
 NUM_TRAIN_TIMESTEPS = 1000
@@ -571,9 +572,9 @@ def convert_ldm_clip_checkpoint_v1(checkpoint):
         if key.startswith("cond_stage_model.transformer"):
             text_model_dict[key[len("cond_stage_model.transformer.") :]] = checkpoint[key]
 
-    # support checkpoint without position_ids (invalid checkpoint)
-    if "text_model.embeddings.position_ids" not in text_model_dict:
-        text_model_dict["text_model.embeddings.position_ids"] = torch.arange(77).unsqueeze(0)  # 77 is the max length of the text
+    # remove position_ids for newer transformer, which causes error :(
+    if "text_model.embeddings.position_ids" in text_model_dict:
+        text_model_dict.pop("text_model.embeddings.position_ids")
 
     return text_model_dict
 
@@ -947,7 +948,7 @@ def convert_vae_state_dict(vae_state_dict):
     for k, v in new_state_dict.items():
         for weight_name in weights_to_convert:
             if f"mid.attn_1.{weight_name}.weight" in k:
-                # print(f"Reshaping {k} for SD format: shape {v.shape} -> {v.shape} x 1 x 1")
+                # logger.info(f"Reshaping {k} for SD format: shape {v.shape} -> {v.shape} x 1 x 1")
                 new_state_dict[k] = reshape_weight_for_sd(v)
 
     return new_state_dict
@@ -1005,7 +1006,7 @@ def load_models_from_stable_diffusion_checkpoint(v2, ckpt_path, device="cpu", dt
 
     unet = UNet2DConditionModel(**unet_config).to(device)
     info = unet.load_state_dict(converted_unet_checkpoint)
-    print("loading u-net:", info)
+    logger.info(f"loading u-net: {info}")
 
     # Convert the VAE model.
     vae_config = create_vae_diffusers_config()
@@ -1013,7 +1014,7 @@ def load_models_from_stable_diffusion_checkpoint(v2, ckpt_path, device="cpu", dt
 
     vae = AutoencoderKL(**vae_config).to(device)
     info = vae.load_state_dict(converted_vae_checkpoint)
-    print("loading vae:", info)
+    logger.info(f"loading vae: {info}")
 
     # convert text_model
     if v2:
@@ -1047,7 +1048,7 @@ def load_models_from_stable_diffusion_checkpoint(v2, ckpt_path, device="cpu", dt
         # logging.set_verbosity_error()  # don't show annoying warning
         # text_model = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14").to(device)
         # logging.set_verbosity_warning()
-        # print(f"config: {text_model.config}")
+        # logger.info(f"config: {text_model.config}")
         cfg = CLIPTextConfig(
             vocab_size=49408,
             hidden_size=768,
@@ -1070,7 +1071,7 @@ def load_models_from_stable_diffusion_checkpoint(v2, ckpt_path, device="cpu", dt
         )
         text_model = CLIPTextModel._from_config(cfg)
         info = text_model.load_state_dict(converted_text_encoder_checkpoint)
-    print("loading text encoder:", info)
+    logger.info(f"loading text encoder: {info}")
 
     return text_model, vae, unet
 
@@ -1145,7 +1146,7 @@ def convert_text_encoder_state_dict_to_sd_v2(checkpoint, make_dummy_weights=Fals
 
     # 最後の層などを捏造するか
     if make_dummy_weights:
-        print("make dummy weights for resblock.23, text_projection and logit scale.")
+        logger.info("make dummy weights for resblock.23, text_projection and logit scale.")
         keys = list(new_sd.keys())
         for key in keys:
             if key.startswith("transformer.resblocks.22."):
@@ -1242,8 +1243,13 @@ def save_diffusers_checkpoint(v2, output_dir, text_encoder, unet, pretrained_mod
     if vae is None:
         vae = AutoencoderKL.from_pretrained(pretrained_model_name_or_path, subfolder="vae")
 
+    # original U-Net cannot be saved, so we need to convert it to the Diffusers version
+    # TODO this consumes a lot of memory
+    diffusers_unet = diffusers.UNet2DConditionModel.from_pretrained(pretrained_model_name_or_path, subfolder="unet")
+    diffusers_unet.load_state_dict(unet.state_dict())
+
     pipeline = StableDiffusionPipeline(
-        unet=unet,
+        unet=diffusers_unet,
         text_encoder=text_encoder,
         vae=vae,
         scheduler=scheduler,
@@ -1259,14 +1265,14 @@ VAE_PREFIX = "first_stage_model."
 
 
 def load_vae(vae_id, dtype):
-    print(f"load VAE: {vae_id}")
+    logger.info(f"load VAE: {vae_id}")
     if os.path.isdir(vae_id) or not os.path.isfile(vae_id):
         # Diffusers local/remote
         try:
             vae = AutoencoderKL.from_pretrained(vae_id, subfolder=None, torch_dtype=dtype)
         except EnvironmentError as e:
-            print(f"exception occurs in loading vae: {e}")
-            print("retry with subfolder='vae'")
+            logger.error(f"exception occurs in loading vae: {e}")
+            logger.error("retry with subfolder='vae'")
             vae = AutoencoderKL.from_pretrained(vae_id, subfolder="vae", torch_dtype=dtype)
         return vae
 
@@ -1307,19 +1313,19 @@ def load_vae(vae_id, dtype):
 
 def make_bucket_resolutions(max_reso, min_size=256, max_size=1024, divisible=64):
     max_width, max_height = max_reso
-    max_area = (max_width // divisible) * (max_height // divisible)
+    max_area = max_width * max_height
 
     resos = set()
 
-    size = int(math.sqrt(max_area)) * divisible
-    resos.add((size, size))
+    width = int(math.sqrt(max_area) // divisible) * divisible
+    resos.add((width, width))
 
-    size = min_size
-    while size <= max_size:
-        width = size
-        height = min(max_size, (max_area // (width // divisible)) * divisible)
-        resos.add((width, height))
-        resos.add((height, width))
+    width = min_size
+    while width <= max_size:
+        height = min(max_size, int((max_area // width) // divisible) * divisible)
+        if height >= min_size:
+            resos.add((width, height))
+            resos.add((height, width))
 
         # # make additional resos
         # if width >= height and width - divisible >= min_size:
@@ -1329,7 +1335,7 @@ def make_bucket_resolutions(max_reso, min_size=256, max_size=1024, divisible=64)
         #   resos.add((width, height - divisible))
         #   resos.add((height - divisible, width))
 
-        size += divisible
+        width += divisible
 
     resos = list(resos)
     resos.sort()
@@ -1338,13 +1344,13 @@ def make_bucket_resolutions(max_reso, min_size=256, max_size=1024, divisible=64)
 
 if __name__ == "__main__":
     resos = make_bucket_resolutions((512, 768))
-    print(len(resos))
-    print(resos)
+    logger.info(f"{len(resos)}")
+    logger.info(f"{resos}")
     aspect_ratios = [w / h for w, h in resos]
-    print(aspect_ratios)
+    logger.info(f"{aspect_ratios}")
 
     ars = set()
     for ar in aspect_ratios:
         if ar in ars:
-            print("error! duplicate ar:", ar)
+            logger.error(f"error! duplicate ar: {ar}")
         ars.add(ar)

library/original_unet.py

@@ -113,6 +113,10 @@ import torch
 from torch import nn
 from torch.nn import functional as F
 from einops import rearrange
+from library.utils import setup_logging
+setup_logging()
+import logging
+logger = logging.getLogger(__name__)
 
 BLOCK_OUT_CHANNELS: Tuple[int] = (320, 640, 1280, 1280)
 TIMESTEP_INPUT_DIM = BLOCK_OUT_CHANNELS[0]
@@ -361,6 +365,23 @@ def get_timestep_embedding(
     return emb
 
 
+# Deep Shrink: We do not common this function, because minimize dependencies.
+def resize_like(x, target, mode="bicubic", align_corners=False):
+    org_dtype = x.dtype
+    if org_dtype == torch.bfloat16:
+        x = x.to(torch.float32)
+
+    if x.shape[-2:] != target.shape[-2:]:
+        if mode == "nearest":
+            x = F.interpolate(x, size=target.shape[-2:], mode=mode)
+        else:
+            x = F.interpolate(x, size=target.shape[-2:], mode=mode, align_corners=align_corners)
+
+    if org_dtype == torch.bfloat16:
+        x = x.to(org_dtype)
+    return x
+
+
 class SampleOutput:
     def __init__(self, sample):
         self.sample = sample
@@ -569,6 +590,9 @@ class CrossAttention(nn.Module):
         self.use_memory_efficient_attention_mem_eff = False
         self.use_sdpa = False
 
+        # Attention processor
+        self.processor = None
+
     def set_use_memory_efficient_attention(self, xformers, mem_eff):
         self.use_memory_efficient_attention_xformers = xformers
         self.use_memory_efficient_attention_mem_eff = mem_eff
@@ -590,7 +614,28 @@ class CrossAttention(nn.Module):
         tensor = tensor.permute(0, 2, 1, 3).reshape(batch_size // head_size, seq_len, dim * head_size)
         return tensor
 
-    def forward(self, hidden_states, context=None, mask=None):
+    def set_processor(self):
+        return self.processor
+
+    def get_processor(self):
+        return self.processor
+
+    def forward(self, hidden_states, context=None, mask=None, **kwargs):
+        if self.processor is not None:
+            (
+                hidden_states,
+                encoder_hidden_states,
+                attention_mask,
+            ) = translate_attention_names_from_diffusers(
+                hidden_states=hidden_states, context=context, mask=mask, **kwargs
+            )
+            return self.processor(
+                attn=self,
+                hidden_states=hidden_states,
+                encoder_hidden_states=context,
+                attention_mask=mask,
+                **kwargs
+            )
         if self.use_memory_efficient_attention_xformers:
             return self.forward_memory_efficient_xformers(hidden_states, context, mask)
         if self.use_memory_efficient_attention_mem_eff:
@@ -703,6 +748,21 @@ class CrossAttention(nn.Module):
         out = self.to_out[0](out)
         return out
 
+def translate_attention_names_from_diffusers(
+    hidden_states: torch.FloatTensor,
+    context: Optional[torch.FloatTensor] = None,
+    mask: Optional[torch.FloatTensor] = None,
+    # HF naming
+    encoder_hidden_states: Optional[torch.FloatTensor] = None,
+    attention_mask: Optional[torch.FloatTensor] = None
+):
+    # translate from hugging face diffusers
+    context = context if context is not None else encoder_hidden_states
+
+    # translate from hugging face diffusers
+    mask = mask if mask is not None else attention_mask
+
+    return hidden_states, context, mask
 
 # feedforward
 class GEGLU(nn.Module):
@@ -1130,6 +1190,7 @@ class UpBlock2D(nn.Module):
             # pop res hidden states
             res_hidden_states = res_hidden_states_tuple[-1]
             res_hidden_states_tuple = res_hidden_states_tuple[:-1]
+
             hidden_states = torch.cat([hidden_states, res_hidden_states], dim=1)
 
             if self.training and self.gradient_checkpointing:
@@ -1205,9 +1266,9 @@ class CrossAttnUpBlock2D(nn.Module):
         for attn in self.attentions:
             attn.set_use_memory_efficient_attention(xformers, mem_eff)
 
-    def set_use_sdpa(self, spda):
+    def set_use_sdpa(self, sdpa):
         for attn in self.attentions:
-            attn.set_use_sdpa(spda)
+            attn.set_use_sdpa(sdpa)
 
     def forward(
         self,
@@ -1221,6 +1282,7 @@ class CrossAttnUpBlock2D(nn.Module):
             # pop res hidden states
             res_hidden_states = res_hidden_states_tuple[-1]
             res_hidden_states_tuple = res_hidden_states_tuple[:-1]
+
             hidden_states = torch.cat([hidden_states, res_hidden_states], dim=1)
 
             if self.training and self.gradient_checkpointing:
@@ -1322,7 +1384,7 @@ class UNet2DConditionModel(nn.Module):
     ):
         super().__init__()
         assert sample_size is not None, "sample_size must be specified"
-        print(
+        logger.info(
             f"UNet2DConditionModel: {sample_size}, {attention_head_dim}, {cross_attention_dim}, {use_linear_projection}, {upcast_attention}"
         )
 
@@ -1331,7 +1393,7 @@ class UNet2DConditionModel(nn.Module):
         self.out_channels = OUT_CHANNELS
 
         self.sample_size = sample_size
-        self.prepare_config()
+        self.prepare_config(sample_size=sample_size)
 
         # state_dictの書式が変わるのでmoduleの持ち方は変えられない
 
@@ -1418,8 +1480,8 @@ class UNet2DConditionModel(nn.Module):
         self.conv_out = nn.Conv2d(BLOCK_OUT_CHANNELS[0], OUT_CHANNELS, kernel_size=3, padding=1)
 
     # region diffusers compatibility
-    def prepare_config(self):
-        self.config = SimpleNamespace()
+    def prepare_config(self, *args, **kwargs):
+        self.config = SimpleNamespace(**kwargs)
 
     @property
     def dtype(self) -> torch.dtype:
@@ -1456,7 +1518,7 @@ class UNet2DConditionModel(nn.Module):
     def set_gradient_checkpointing(self, value=False):
         modules = self.down_blocks + [self.mid_block] + self.up_blocks
         for module in modules:
-            print(module.__class__.__name__, module.gradient_checkpointing, "->", value)
+            logger.info(f"{module.__class__.__name__} {module.gradient_checkpointing} -> {value}")
             module.gradient_checkpointing = value
 
     # endregion
@@ -1519,7 +1581,6 @@ class UNet2DConditionModel(nn.Module):
         # 2. pre-process
         sample = self.conv_in(sample)
 
-        # 3. down
         down_block_res_samples = (sample,)
         for downsample_block in self.down_blocks:
             # downblockはforwardで必ずencoder_hidden_statesを受け取るようにしても良さそうだけど、
@@ -1604,3 +1665,255 @@ class UNet2DConditionModel(nn.Module):
         timesteps = timesteps.expand(sample.shape[0])
 
         return timesteps
+
+
+class InferUNet2DConditionModel:
+    def __init__(self, original_unet: UNet2DConditionModel):
+        self.delegate = original_unet
+
+        # override original model's forward method: because forward is not called by `__call__`
+        # overriding `__call__` is not enough, because nn.Module.forward has a special handling
+        self.delegate.forward = self.forward
+
+        # override original model's up blocks' forward method
+        for up_block in self.delegate.up_blocks:
+            if up_block.__class__.__name__ == "UpBlock2D":
+
+                def resnet_wrapper(func, block):
+                    def forward(*args, **kwargs):
+                        return func(block, *args, **kwargs)
+
+                    return forward
+
+                up_block.forward = resnet_wrapper(self.up_block_forward, up_block)
+
+            elif up_block.__class__.__name__ == "CrossAttnUpBlock2D":
+
+                def cross_attn_up_wrapper(func, block):
+                    def forward(*args, **kwargs):
+                        return func(block, *args, **kwargs)
+
+                    return forward
+
+                up_block.forward = cross_attn_up_wrapper(self.cross_attn_up_block_forward, up_block)
+
+        # Deep Shrink
+        self.ds_depth_1 = None
+        self.ds_depth_2 = None
+        self.ds_timesteps_1 = None
+        self.ds_timesteps_2 = None
+        self.ds_ratio = None
+
+    # call original model's methods
+    def __getattr__(self, name):
+        return getattr(self.delegate, name)
+
+    def __call__(self, *args, **kwargs):
+        return self.delegate(*args, **kwargs)
+
+    def set_deep_shrink(self, ds_depth_1, ds_timesteps_1=650, ds_depth_2=None, ds_timesteps_2=None, ds_ratio=0.5):
+        if ds_depth_1 is None:
+            logger.info("Deep Shrink is disabled.")
+            self.ds_depth_1 = None
+            self.ds_timesteps_1 = None
+            self.ds_depth_2 = None
+            self.ds_timesteps_2 = None
+            self.ds_ratio = None
+        else:
+            logger.info(
+                f"Deep Shrink is enabled: [depth={ds_depth_1}/{ds_depth_2}, timesteps={ds_timesteps_1}/{ds_timesteps_2}, ratio={ds_ratio}]"
+            )
+            self.ds_depth_1 = ds_depth_1
+            self.ds_timesteps_1 = ds_timesteps_1
+            self.ds_depth_2 = ds_depth_2 if ds_depth_2 is not None else -1
+            self.ds_timesteps_2 = ds_timesteps_2 if ds_timesteps_2 is not None else 1000
+            self.ds_ratio = ds_ratio
+
+    def up_block_forward(self, _self, hidden_states, res_hidden_states_tuple, temb=None, upsample_size=None):
+        for resnet in _self.resnets:
+            # pop res hidden states
+            res_hidden_states = res_hidden_states_tuple[-1]
+            res_hidden_states_tuple = res_hidden_states_tuple[:-1]
+
+            # Deep Shrink
+            if res_hidden_states.shape[-2:] != hidden_states.shape[-2:]:
+                hidden_states = resize_like(hidden_states, res_hidden_states)
+
+            hidden_states = torch.cat([hidden_states, res_hidden_states], dim=1)
+            hidden_states = resnet(hidden_states, temb)
+
+        if _self.upsamplers is not None:
+            for upsampler in _self.upsamplers:
+                hidden_states = upsampler(hidden_states, upsample_size)
+
+        return hidden_states
+
+    def cross_attn_up_block_forward(
+        self,
+        _self,
+        hidden_states,
+        res_hidden_states_tuple,
+        temb=None,
+        encoder_hidden_states=None,
+        upsample_size=None,
+    ):
+        for resnet, attn in zip(_self.resnets, _self.attentions):
+            # pop res hidden states
+            res_hidden_states = res_hidden_states_tuple[-1]
+            res_hidden_states_tuple = res_hidden_states_tuple[:-1]
+
+            # Deep Shrink
+            if res_hidden_states.shape[-2:] != hidden_states.shape[-2:]:
+                hidden_states = resize_like(hidden_states, res_hidden_states)
+
+            hidden_states = torch.cat([hidden_states, res_hidden_states], dim=1)
+            hidden_states = resnet(hidden_states, temb)
+            hidden_states = attn(hidden_states, encoder_hidden_states=encoder_hidden_states).sample
+
+        if _self.upsamplers is not None:
+            for upsampler in _self.upsamplers:
+                hidden_states = upsampler(hidden_states, upsample_size)
+
+        return hidden_states
+
+    def forward(
+        self,
+        sample: torch.FloatTensor,
+        timestep: Union[torch.Tensor, float, int],
+        encoder_hidden_states: torch.Tensor,
+        class_labels: Optional[torch.Tensor] = None,
+        return_dict: bool = True,
+        down_block_additional_residuals: Optional[Tuple[torch.Tensor]] = None,
+        mid_block_additional_residual: Optional[torch.Tensor] = None,
+    ) -> Union[Dict, Tuple]:
+        r"""
+        current implementation is a copy of `UNet2DConditionModel.forward()` with Deep Shrink.
+        """
+
+        r"""
+        Args:
+            sample (`torch.FloatTensor`): (batch, channel, height, width) noisy inputs tensor
+            timestep (`torch.FloatTensor` or `float` or `int`): (batch) timesteps
+            encoder_hidden_states (`torch.FloatTensor`): (batch, sequence_length, feature_dim) encoder hidden states
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a dict instead of a plain tuple.
+
+        Returns:
+            `SampleOutput` or `tuple`:
+            `SampleOutput` if `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is the sample tensor.
+        """
+
+        _self = self.delegate
+
+        # By default samples have to be AT least a multiple of the overall upsampling factor.
+        # The overall upsampling factor is equal to 2 ** (# num of upsampling layears).
+        # However, the upsampling interpolation output size can be forced to fit any upsampling size
+        # on the fly if necessary.
+        # デフォルトではサンプルは「2^アップサンプルの数」、つまり64の倍数である必要がある
+        # ただそれ以外のサイズにも対応できるように、必要ならアップサンプルのサイズを変更する
+        # 多分画質が悪くなるので、64で割り切れるようにしておくのが良い
+        default_overall_up_factor = 2**_self.num_upsamplers
+
+        # upsample size should be forwarded when sample is not a multiple of `default_overall_up_factor`
+        # 64で割り切れないときはupsamplerにサイズを伝える
+        forward_upsample_size = False
+        upsample_size = None
+
+        if any(s % default_overall_up_factor != 0 for s in sample.shape[-2:]):
+            # logger.info("Forward upsample size to force interpolation output size.")
+            forward_upsample_size = True
+
+        # 1. time
+        timesteps = timestep
+        timesteps = _self.handle_unusual_timesteps(sample, timesteps)  # 変な時だけ処理
+
+        t_emb = _self.time_proj(timesteps)
+
+        # timesteps does not contain any weights and will always return f32 tensors
+        # but time_embedding might actually be running in fp16. so we need to cast here.
+        # there might be better ways to encapsulate this.
+        # timestepsは重みを含まないので常にfloat32のテンソルを返す
+        # しかしtime_embeddingはfp16で動いているかもしれないので、ここでキャストする必要がある
+        # time_projでキャストしておけばいいんじゃね？
+        t_emb = t_emb.to(dtype=_self.dtype)
+        emb = _self.time_embedding(t_emb)
+
+        # 2. pre-process
+        sample = _self.conv_in(sample)
+
+        down_block_res_samples = (sample,)
+        for depth, downsample_block in enumerate(_self.down_blocks):
+            # Deep Shrink
+            if self.ds_depth_1 is not None:
+                if (depth == self.ds_depth_1 and timesteps[0] >= self.ds_timesteps_1) or (
+                    self.ds_depth_2 is not None
+                    and depth == self.ds_depth_2
+                    and timesteps[0] < self.ds_timesteps_1
+                    and timesteps[0] >= self.ds_timesteps_2
+                ):
+                    org_dtype = sample.dtype
+                    if org_dtype == torch.bfloat16:
+                        sample = sample.to(torch.float32)
+                    sample = F.interpolate(sample, scale_factor=self.ds_ratio, mode="bicubic", align_corners=False).to(org_dtype)
+
+            # downblockはforwardで必ずencoder_hidden_statesを受け取るようにしても良さそうだけど、
+            # まあこちらのほうがわかりやすいかもしれない
+            if downsample_block.has_cross_attention:
+                sample, res_samples = downsample_block(
+                    hidden_states=sample,
+                    temb=emb,
+                    encoder_hidden_states=encoder_hidden_states,
+                )
+            else:
+                sample, res_samples = downsample_block(hidden_states=sample, temb=emb)
+
+            down_block_res_samples += res_samples
+
+        # skip connectionにControlNetの出力を追加する
+        if down_block_additional_residuals is not None:
+            down_block_res_samples = list(down_block_res_samples)
+            for i in range(len(down_block_res_samples)):
+                down_block_res_samples[i] += down_block_additional_residuals[i]
+            down_block_res_samples = tuple(down_block_res_samples)
+
+        # 4. mid
+        sample = _self.mid_block(sample, emb, encoder_hidden_states=encoder_hidden_states)
+
+        # ControlNetの出力を追加する
+        if mid_block_additional_residual is not None:
+            sample += mid_block_additional_residual
+
+        # 5. up
+        for i, upsample_block in enumerate(_self.up_blocks):
+            is_final_block = i == len(_self.up_blocks) - 1
+
+            res_samples = down_block_res_samples[-len(upsample_block.resnets) :]
+            down_block_res_samples = down_block_res_samples[: -len(upsample_block.resnets)]  # skip connection
+
+            # if we have not reached the final block and need to forward the upsample size, we do it here
+            # 前述のように最後のブロック以外ではupsample_sizeを伝える
+            if not is_final_block and forward_upsample_size:
+                upsample_size = down_block_res_samples[-1].shape[2:]
+
+            if upsample_block.has_cross_attention:
+                sample = upsample_block(
+                    hidden_states=sample,
+                    temb=emb,
+                    res_hidden_states_tuple=res_samples,
+                    encoder_hidden_states=encoder_hidden_states,
+                    upsample_size=upsample_size,
+                )
+            else:
+                sample = upsample_block(
+                    hidden_states=sample, temb=emb, res_hidden_states_tuple=res_samples, upsample_size=upsample_size
+                )
+
+        # 6. post-process
+        sample = _self.conv_norm_out(sample)
+        sample = _self.conv_act(sample)
+        sample = _self.conv_out(sample)
+
+        if not return_dict:
+            return (sample,)
+
+        return SampleOutput(sample=sample)

library/sai_model_spec.py

@@ -5,6 +5,10 @@ from io import BytesIO
 import os
 from typing import List, Optional, Tuple, Union
 import safetensors
+from library.utils import setup_logging
+setup_logging()
+import logging
+logger = logging.getLogger(__name__)
 
 r"""
 # Metadata Example
@@ -231,7 +235,7 @@ def build_metadata(
     # # assert all values are filled
     # assert all([v is not None for v in metadata.values()]), metadata
     if not all([v is not None for v in metadata.values()]):
-        print(f"Internal error: some metadata values are None: {metadata}")
+        logger.error(f"Internal error: some metadata values are None: {metadata}")
     
     return metadata
 

library/sdxl_lpw_stable_diffusion.py

@@ -923,7 +923,11 @@ class SdxlStableDiffusionLongPromptWeightingPipeline:
             if up1 is not None:
                 uncond_pool = up1
 
-        dtype = self.unet.dtype
+        unet_dtype = self.unet.dtype
+        dtype = unet_dtype
+        if hasattr(dtype, "itemsize") and dtype.itemsize == 1:  # fp8
+            dtype = torch.float16
+            self.unet.to(dtype)
 
         # 4. Preprocess image and mask
         if isinstance(image, PIL.Image.Image):
@@ -1028,6 +1032,7 @@ class SdxlStableDiffusionLongPromptWeightingPipeline:
                 if is_cancelled_callback is not None and is_cancelled_callback():
                     return None
 
+        self.unet.to(unet_dtype)
         return latents
 
     def latents_to_image(self, latents):

library/sdxl_model_util.py

@@ -7,7 +7,10 @@ from typing import List
 from diffusers import AutoencoderKL, EulerDiscreteScheduler, UNet2DConditionModel
 from library import model_util
 from library import sdxl_original_unet
-
+from .utils import setup_logging
+setup_logging()
+import logging
+logger = logging.getLogger(__name__)
 
 VAE_SCALE_FACTOR = 0.13025
 MODEL_VERSION_SDXL_BASE_V1_0 = "sdxl_base_v1-0"
@@ -100,7 +103,7 @@ def convert_sdxl_text_encoder_2_checkpoint(checkpoint, max_length):
             key = key.replace(".ln_final", ".final_layer_norm")
         # ckpt from comfy has this key: text_model.encoder.text_model.embeddings.position_ids
         elif ".embeddings.position_ids" in key:
-            key = None  # remove this key: make position_ids by ourselves
+            key = None  # remove this key: position_ids is not used in newer transformers
         return key
 
     keys = list(checkpoint.keys())
@@ -126,13 +129,15 @@ def convert_sdxl_text_encoder_2_checkpoint(checkpoint, max_length):
             new_sd[key_pfx + "k_proj" + key_suffix] = values[1]
             new_sd[key_pfx + "v_proj" + key_suffix] = values[2]
 
-    # original SD にはないので、position_idsを追加
-    position_ids = torch.Tensor([list(range(max_length))]).to(torch.int64)
-    new_sd["text_model.embeddings.position_ids"] = position_ids
-
     # logit_scale はDiffusersには含まれないが、保存時に戻したいので別途返す
     logit_scale = checkpoint.get(SDXL_KEY_PREFIX + "logit_scale", None)
 
+    # temporary workaround for text_projection.weight.weight for Playground-v2
+    if "text_projection.weight.weight" in new_sd:
+        logger.info("convert_sdxl_text_encoder_2_checkpoint: convert text_projection.weight.weight to text_projection.weight")
+        new_sd["text_projection.weight"] = new_sd["text_projection.weight.weight"]
+        del new_sd["text_projection.weight.weight"]
+
     return new_sd, logit_scale
 
 
@@ -184,20 +189,20 @@ def load_models_from_sdxl_checkpoint(model_version, ckpt_path, map_location, dty
         checkpoint = None
 
     # U-Net
-    print("building U-Net")
+    logger.info("building U-Net")
     with init_empty_weights():
         unet = sdxl_original_unet.SdxlUNet2DConditionModel()
 
-    print("loading U-Net from checkpoint")
+    logger.info("loading U-Net from checkpoint")
     unet_sd = {}
     for k in list(state_dict.keys()):
         if k.startswith("model.diffusion_model."):
             unet_sd[k.replace("model.diffusion_model.", "")] = state_dict.pop(k)
     info = _load_state_dict_on_device(unet, unet_sd, device=map_location, dtype=dtype)
-    print("U-Net: ", info)
+    logger.info(f"U-Net: {info}")
 
     # Text Encoders
-    print("building text encoders")
+    logger.info("building text encoders")
 
     # Text Encoder 1 is same to Stability AI's SDXL
     text_model1_cfg = CLIPTextConfig(
@@ -250,7 +255,7 @@ def load_models_from_sdxl_checkpoint(model_version, ckpt_path, map_location, dty
     with init_empty_weights():
         text_model2 = CLIPTextModelWithProjection(text_model2_cfg)
 
-    print("loading text encoders from checkpoint")
+    logger.info("loading text encoders from checkpoint")
     te1_sd = {}
     te2_sd = {}
     for k in list(state_dict.keys()):
@@ -258,28 +263,28 @@ def load_models_from_sdxl_checkpoint(model_version, ckpt_path, map_location, dty
             te1_sd[k.replace("conditioner.embedders.0.transformer.", "")] = state_dict.pop(k)
         elif k.startswith("conditioner.embedders.1.model."):
             te2_sd[k] = state_dict.pop(k)
-    
-    # 一部のposition_idsがないモデルへの対応 / add position_ids for some models
-    if "text_model.embeddings.position_ids" not in te1_sd:
-        te1_sd["text_model.embeddings.position_ids"] = torch.arange(77).unsqueeze(0)
+
+    # 最新の transformers では position_ids を含むとエラーになるので削除 / remove position_ids for latest transformers
+    if "text_model.embeddings.position_ids" in te1_sd:
+        te1_sd.pop("text_model.embeddings.position_ids")
 
     info1 = _load_state_dict_on_device(text_model1, te1_sd, device=map_location)  # remain fp32
-    print("text encoder 1:", info1)
+    logger.info(f"text encoder 1: {info1}")
 
     converted_sd, logit_scale = convert_sdxl_text_encoder_2_checkpoint(te2_sd, max_length=77)
     info2 = _load_state_dict_on_device(text_model2, converted_sd, device=map_location)  # remain fp32
-    print("text encoder 2:", info2)
+    logger.info(f"text encoder 2: {info2}")
 
     # prepare vae
-    print("building VAE")
+    logger.info("building VAE")
     vae_config = model_util.create_vae_diffusers_config()
     with init_empty_weights():
         vae = AutoencoderKL(**vae_config)
 
-    print("loading VAE from checkpoint")
+    logger.info("loading VAE from checkpoint")
     converted_vae_checkpoint = model_util.convert_ldm_vae_checkpoint(state_dict, vae_config)
     info = _load_state_dict_on_device(vae, converted_vae_checkpoint, device=map_location, dtype=dtype)
-    print("VAE:", info)
+    logger.info(f"VAE: {info}")
 
     ckpt_info = (epoch, global_step) if epoch is not None else None
     return text_model1, text_model2, vae, unet, logit_scale, ckpt_info

library/sdxl_original_unet.py

@@ -24,13 +24,18 @@
 
 import math
 from types import SimpleNamespace
-from typing import Optional
+from typing import Any, Optional
 import torch
 import torch.utils.checkpoint
 from torch import nn
 from torch.nn import functional as F
 from einops import rearrange
+from .utils import setup_logging
 
+setup_logging()
+import logging
+
+logger = logging.getLogger(__name__)
 
 IN_CHANNELS: int = 4
 OUT_CHANNELS: int = 4
@@ -266,6 +271,23 @@ def get_timestep_embedding(
     return emb
 
 
+# Deep Shrink: We do not common this function, because minimize dependencies.
+def resize_like(x, target, mode="bicubic", align_corners=False):
+    org_dtype = x.dtype
+    if org_dtype == torch.bfloat16:
+        x = x.to(torch.float32)
+
+    if x.shape[-2:] != target.shape[-2:]:
+        if mode == "nearest":
+            x = F.interpolate(x, size=target.shape[-2:], mode=mode)
+        else:
+            x = F.interpolate(x, size=target.shape[-2:], mode=mode, align_corners=align_corners)
+
+    if org_dtype == torch.bfloat16:
+        x = x.to(org_dtype)
+    return x
+
+
 class GroupNorm32(nn.GroupNorm):
     def forward(self, x):
         if self.weight.dtype != torch.float32:
@@ -315,7 +337,7 @@ class ResnetBlock2D(nn.Module):
 
     def forward(self, x, emb):
         if self.training and self.gradient_checkpointing:
-            # print("ResnetBlock2D: gradient_checkpointing")
+            # logger.info("ResnetBlock2D: gradient_checkpointing")
 
             def create_custom_forward(func):
                 def custom_forward(*inputs):
@@ -349,7 +371,7 @@ class Downsample2D(nn.Module):
 
     def forward(self, hidden_states):
         if self.training and self.gradient_checkpointing:
-            # print("Downsample2D: gradient_checkpointing")
+            # logger.info("Downsample2D: gradient_checkpointing")
 
             def create_custom_forward(func):
                 def custom_forward(*inputs):
@@ -636,7 +658,7 @@ class BasicTransformerBlock(nn.Module):
 
     def forward(self, hidden_states, context=None, timestep=None):
         if self.training and self.gradient_checkpointing:
-            # print("BasicTransformerBlock: checkpointing")
+            # logger.info("BasicTransformerBlock: checkpointing")
 
             def create_custom_forward(func):
                 def custom_forward(*inputs):
@@ -779,7 +801,7 @@ class Upsample2D(nn.Module):
 
     def forward(self, hidden_states, output_size=None):
         if self.training and self.gradient_checkpointing:
-            # print("Upsample2D: gradient_checkpointing")
+            # logger.info("Upsample2D: gradient_checkpointing")
 
             def create_custom_forward(func):
                 def custom_forward(*inputs):
@@ -1029,7 +1051,7 @@ class SdxlUNet2DConditionModel(nn.Module):
         for block in blocks:
             for module in block:
                 if hasattr(module, "set_use_memory_efficient_attention"):
-                    # print(module.__class__.__name__)
+                    # logger.info(module.__class__.__name__)
                     module.set_use_memory_efficient_attention(xformers, mem_eff)
 
     def set_use_sdpa(self, sdpa: bool) -> None:
@@ -1044,7 +1066,7 @@ class SdxlUNet2DConditionModel(nn.Module):
         for block in blocks:
             for module in block.modules():
                 if hasattr(module, "gradient_checkpointing"):
-                    # print(module.__class__.__name__, module.gradient_checkpointing, "->", value)
+                    # logger.info(f{module.__class__.__name__} {module.gradient_checkpointing} -> {value}")
                     module.gradient_checkpointing = value
 
     # endregion
@@ -1054,7 +1076,7 @@ class SdxlUNet2DConditionModel(nn.Module):
         timesteps = timesteps.expand(x.shape[0])
 
         hs = []
-        t_emb = get_timestep_embedding(timesteps, self.model_channels)  # , repeat_only=False)
+        t_emb = get_timestep_embedding(timesteps, self.model_channels, downscale_freq_shift=0)  # , repeat_only=False)
         t_emb = t_emb.to(x.dtype)
         emb = self.time_embed(t_emb)
 
@@ -1066,7 +1088,7 @@ class SdxlUNet2DConditionModel(nn.Module):
         def call_module(module, h, emb, context):
             x = h
             for layer in module:
-                # print(layer.__class__.__name__, x.dtype, emb.dtype, context.dtype if context is not None else None)
+                # logger.info(layer.__class__.__name__, x.dtype, emb.dtype, context.dtype if context is not None else None)
                 if isinstance(layer, ResnetBlock2D):
                     x = layer(x, emb)
                 elif isinstance(layer, Transformer2DModel):
@@ -1077,6 +1099,7 @@ class SdxlUNet2DConditionModel(nn.Module):
 
         # h = x.type(self.dtype)
         h = x
+
         for module in self.input_blocks:
             h = call_module(module, h, emb, context)
             hs.append(h)
@@ -1093,10 +1116,125 @@ class SdxlUNet2DConditionModel(nn.Module):
         return h
 
 
+class InferSdxlUNet2DConditionModel:
+    def __init__(self, original_unet: SdxlUNet2DConditionModel, **kwargs):
+        self.delegate = original_unet
+
+        # override original model's forward method: because forward is not called by `__call__`
+        # overriding `__call__` is not enough, because nn.Module.forward has a special handling
+        self.delegate.forward = self.forward
+
+        # Deep Shrink
+        self.ds_depth_1 = None
+        self.ds_depth_2 = None
+        self.ds_timesteps_1 = None
+        self.ds_timesteps_2 = None
+        self.ds_ratio = None
+
+    # call original model's methods
+    def __getattr__(self, name):
+        return getattr(self.delegate, name)
+
+    def __call__(self, *args, **kwargs):
+        return self.delegate(*args, **kwargs)
+
+    def set_deep_shrink(self, ds_depth_1, ds_timesteps_1=650, ds_depth_2=None, ds_timesteps_2=None, ds_ratio=0.5):
+        if ds_depth_1 is None:
+            logger.info("Deep Shrink is disabled.")
+            self.ds_depth_1 = None
+            self.ds_timesteps_1 = None
+            self.ds_depth_2 = None
+            self.ds_timesteps_2 = None
+            self.ds_ratio = None
+        else:
+            logger.info(
+                f"Deep Shrink is enabled: [depth={ds_depth_1}/{ds_depth_2}, timesteps={ds_timesteps_1}/{ds_timesteps_2}, ratio={ds_ratio}]"
+            )
+            self.ds_depth_1 = ds_depth_1
+            self.ds_timesteps_1 = ds_timesteps_1
+            self.ds_depth_2 = ds_depth_2 if ds_depth_2 is not None else -1
+            self.ds_timesteps_2 = ds_timesteps_2 if ds_timesteps_2 is not None else 1000
+            self.ds_ratio = ds_ratio
+
+    def forward(self, x, timesteps=None, context=None, y=None, **kwargs):
+        r"""
+        current implementation is a copy of `SdxlUNet2DConditionModel.forward()` with Deep Shrink.
+        """
+        _self = self.delegate
+
+        # broadcast timesteps to batch dimension
+        timesteps = timesteps.expand(x.shape[0])
+
+        hs = []
+        t_emb = get_timestep_embedding(timesteps, _self.model_channels, downscale_freq_shift=0)  # , repeat_only=False)
+        t_emb = t_emb.to(x.dtype)
+        emb = _self.time_embed(t_emb)
+
+        assert x.shape[0] == y.shape[0], f"batch size mismatch: {x.shape[0]} != {y.shape[0]}"
+        assert x.dtype == y.dtype, f"dtype mismatch: {x.dtype} != {y.dtype}"
+        # assert x.dtype == _self.dtype
+        emb = emb + _self.label_emb(y)
+
+        def call_module(module, h, emb, context):
+            x = h
+            for layer in module:
+                # print(layer.__class__.__name__, x.dtype, emb.dtype, context.dtype if context is not None else None)
+                if isinstance(layer, ResnetBlock2D):
+                    x = layer(x, emb)
+                elif isinstance(layer, Transformer2DModel):
+                    x = layer(x, context)
+                else:
+                    x = layer(x)
+            return x
+
+        # h = x.type(self.dtype)
+        h = x
+
+        for depth, module in enumerate(_self.input_blocks):
+            # Deep Shrink
+            if self.ds_depth_1 is not None:
+                if (depth == self.ds_depth_1 and timesteps[0] >= self.ds_timesteps_1) or (
+                    self.ds_depth_2 is not None
+                    and depth == self.ds_depth_2
+                    and timesteps[0] < self.ds_timesteps_1
+                    and timesteps[0] >= self.ds_timesteps_2
+                ):
+                    # print("downsample", h.shape, self.ds_ratio)
+                    org_dtype = h.dtype
+                    if org_dtype == torch.bfloat16:
+                        h = h.to(torch.float32)
+                    h = F.interpolate(h, scale_factor=self.ds_ratio, mode="bicubic", align_corners=False).to(org_dtype)
+
+            h = call_module(module, h, emb, context)
+            hs.append(h)
+
+        h = call_module(_self.middle_block, h, emb, context)
+
+        for module in _self.output_blocks:
+            # Deep Shrink
+            if self.ds_depth_1 is not None:
+                if hs[-1].shape[-2:] != h.shape[-2:]:
+                    # print("upsample", h.shape, hs[-1].shape)
+                    h = resize_like(h, hs[-1])
+
+            h = torch.cat([h, hs.pop()], dim=1)
+            h = call_module(module, h, emb, context)
+
+        # Deep Shrink: in case of depth 0
+        if self.ds_depth_1 == 0 and h.shape[-2:] != x.shape[-2:]:
+            # print("upsample", h.shape, x.shape)
+            h = resize_like(h, x)
+
+        h = h.type(x.dtype)
+        h = call_module(_self.out, h, emb, context)
+
+        return h
+
+
 if __name__ == "__main__":
     import time
 
-    print("create unet")
+    logger.info("create unet")
     unet = SdxlUNet2DConditionModel()
 
     unet.to("cuda")
@@ -1105,7 +1243,7 @@ if __name__ == "__main__":
     unet.train()
 
     # 使用メモリ量確認用の疑似学習ループ
-    print("preparing optimizer")
+    logger.info("preparing optimizer")
 
     # optimizer = torch.optim.SGD(unet.parameters(), lr=1e-3, nesterov=True, momentum=0.9) # not working
 
@@ -1120,12 +1258,12 @@ if __name__ == "__main__":
 
     scaler = torch.cuda.amp.GradScaler(enabled=True)
 
-    print("start training")
+    logger.info("start training")
     steps = 10
     batch_size = 1
 
     for step in range(steps):
-        print(f"step {step}")
+        logger.info(f"step {step}")
         if step == 1:
             time_start = time.perf_counter()
 
@@ -1145,4 +1283,4 @@ if __name__ == "__main__":
         optimizer.zero_grad(set_to_none=True)
 
     time_end = time.perf_counter()
-    print(f"elapsed time: {time_end - time_start} [sec] for last {steps - 1} steps")
+    logger.info(f"elapsed time: {time_end - time_start} [sec] for last {steps - 1} steps")

library/sdxl_train_util.py

@@ -1,14 +1,21 @@
 import argparse
-import gc
 import math
 import os
 from typing import Optional
+
 import torch
+from library.device_utils import init_ipex, clean_memory_on_device
+init_ipex()
+
 from accelerate import init_empty_weights
 from tqdm import tqdm
 from transformers import CLIPTokenizer
 from library import model_util, sdxl_model_util, train_util, sdxl_original_unet
 from library.sdxl_lpw_stable_diffusion import SdxlStableDiffusionLongPromptWeightingPipeline
+from .utils import setup_logging
+setup_logging()
+import logging
+logger = logging.getLogger(__name__)
 
 TOKENIZER1_PATH = "openai/clip-vit-large-patch14"
 TOKENIZER2_PATH = "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k"
@@ -17,11 +24,10 @@ TOKENIZER2_PATH = "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k"
 
 
 def load_target_model(args, accelerator, model_version: str, weight_dtype):
-    # load models for each process
     model_dtype = match_mixed_precision(args, weight_dtype)  # prepare fp16/bf16
     for pi in range(accelerator.state.num_processes):
         if pi == accelerator.state.local_process_index:
-            print(f"loading model for process {accelerator.state.local_process_index}/{accelerator.state.num_processes}")
+            logger.info(f"loading model for process {accelerator.state.local_process_index}/{accelerator.state.num_processes}")
 
             (
                 load_stable_diffusion_format,
@@ -47,12 +53,9 @@ def load_target_model(args, accelerator, model_version: str, weight_dtype):
                 unet.to(accelerator.device)
                 vae.to(accelerator.device)
 
-            gc.collect()
-            torch.cuda.empty_cache()
+            clean_memory_on_device(accelerator.device)
         accelerator.wait_for_everyone()
 
-    text_encoder1, text_encoder2, unet = train_util.transform_models_if_DDP([text_encoder1, text_encoder2, unet])
-
     return load_stable_diffusion_format, text_encoder1, text_encoder2, vae, unet, logit_scale, ckpt_info
 
 
@@ -64,7 +67,7 @@ def _load_target_model(
     load_stable_diffusion_format = os.path.isfile(name_or_path)  # determine SD or Diffusers
 
     if load_stable_diffusion_format:
-        print(f"load StableDiffusion checkpoint: {name_or_path}")
+        logger.info(f"load StableDiffusion checkpoint: {name_or_path}")
         (
             text_encoder1,
             text_encoder2,
@@ -78,7 +81,7 @@ def _load_target_model(
         from diffusers import StableDiffusionXLPipeline
 
         variant = "fp16" if weight_dtype == torch.float16 else None
-        print(f"load Diffusers pretrained models: {name_or_path}, variant={variant}")
+        logger.info(f"load Diffusers pretrained models: {name_or_path}, variant={variant}")
         try:
             try:
                 pipe = StableDiffusionXLPipeline.from_pretrained(
@@ -86,12 +89,12 @@ def _load_target_model(
                 )
             except EnvironmentError as ex:
                 if variant is not None:
-                    print("try to load fp32 model")
+                    logger.info("try to load fp32 model")
                     pipe = StableDiffusionXLPipeline.from_pretrained(name_or_path, variant=None, tokenizer=None)
                 else:
                     raise ex
         except EnvironmentError as ex:
-            print(
+            logger.error(
                 f"model is not found as a file or in Hugging Face, perhaps file name is wrong? / 指定したモデル名のファイル、またはHugging Faceのモデルが見つかりません。ファイル名が誤っているかもしれません: {name_or_path}"
             )
             raise ex
@@ -114,7 +117,7 @@ def _load_target_model(
         with init_empty_weights():
             unet = sdxl_original_unet.SdxlUNet2DConditionModel()  # overwrite unet
         sdxl_model_util._load_state_dict_on_device(unet, state_dict, device=device, dtype=model_dtype)
-        print("U-Net converted to original U-Net")
+        logger.info("U-Net converted to original U-Net")
 
         logit_scale = None
         ckpt_info = None
@@ -122,13 +125,13 @@ def _load_target_model(
     # VAEを読み込む
     if vae_path is not None:
         vae = model_util.load_vae(vae_path, weight_dtype)
-        print("additional VAE loaded")
+        logger.info("additional VAE loaded")
 
     return load_stable_diffusion_format, text_encoder1, text_encoder2, vae, unet, logit_scale, ckpt_info
 
 
 def load_tokenizers(args: argparse.Namespace):
-    print("prepare tokenizers")
+    logger.info("prepare tokenizers")
 
     original_paths = [TOKENIZER1_PATH, TOKENIZER2_PATH]
     tokeniers = []
@@ -137,14 +140,14 @@ def load_tokenizers(args: argparse.Namespace):
         if args.tokenizer_cache_dir:
             local_tokenizer_path = os.path.join(args.tokenizer_cache_dir, original_path.replace("/", "_"))
             if os.path.exists(local_tokenizer_path):
-                print(f"load tokenizer from cache: {local_tokenizer_path}")
+                logger.info(f"load tokenizer from cache: {local_tokenizer_path}")
                 tokenizer = CLIPTokenizer.from_pretrained(local_tokenizer_path)
 
         if tokenizer is None:
             tokenizer = CLIPTokenizer.from_pretrained(original_path)
 
         if args.tokenizer_cache_dir and not os.path.exists(local_tokenizer_path):
-            print(f"save Tokenizer to cache: {local_tokenizer_path}")
+            logger.info(f"save Tokenizer to cache: {local_tokenizer_path}")
             tokenizer.save_pretrained(local_tokenizer_path)
 
         if i == 1:
@@ -153,7 +156,7 @@ def load_tokenizers(args: argparse.Namespace):
         tokeniers.append(tokenizer)
 
     if hasattr(args, "max_token_length") and args.max_token_length is not None:
-        print(f"update token length: {args.max_token_length}")
+        logger.info(f"update token length: {args.max_token_length}")
 
     return tokeniers
 
@@ -334,23 +337,23 @@ def add_sdxl_training_arguments(parser: argparse.ArgumentParser):
 def verify_sdxl_training_args(args: argparse.Namespace, supportTextEncoderCaching: bool = True):
     assert not args.v2, "v2 cannot be enabled in SDXL training / SDXL学習ではv2を有効にすることはできません"
     if args.v_parameterization:
-        print("v_parameterization will be unexpected / SDXL学習ではv_parameterizationは想定外の動作になります")
+        logger.warning("v_parameterization will be unexpected / SDXL学習ではv_parameterizationは想定外の動作になります")
 
     if args.clip_skip is not None:
-        print("clip_skip will be unexpected / SDXL学習ではclip_skipは動作しません")
+        logger.warning("clip_skip will be unexpected / SDXL学習ではclip_skipは動作しません")
 
     # if args.multires_noise_iterations:
-    #     print(
+    #     logger.info(
     #         f"Warning: SDXL has been trained with noise_offset={DEFAULT_NOISE_OFFSET}, but noise_offset is disabled due to multires_noise_iterations / SDXLはnoise_offset={DEFAULT_NOISE_OFFSET}で学習されていますが、multires_noise_iterationsが有効になっているためnoise_offsetは無効になります"
     #     )
     # else:
     #     if args.noise_offset is None:
     #         args.noise_offset = DEFAULT_NOISE_OFFSET
     #     elif args.noise_offset != DEFAULT_NOISE_OFFSET:
-    #         print(
+    #         logger.info(
     #             f"Warning: SDXL has been trained with noise_offset={DEFAULT_NOISE_OFFSET} / SDXLはnoise_offset={DEFAULT_NOISE_OFFSET}で学習されています"
     #         )
-    #     print(f"noise_offset is set to {args.noise_offset} / noise_offsetが{args.noise_offset}に設定されました")
+    #     logger.info(f"noise_offset is set to {args.noise_offset} / noise_offsetが{args.noise_offset}に設定されました")
 
     assert (
         not hasattr(args, "weighted_captions") or not args.weighted_captions
@@ -359,7 +362,7 @@ def verify_sdxl_training_args(args: argparse.Namespace, supportTextEncoderCachin
     if supportTextEncoderCaching:
         if args.cache_text_encoder_outputs_to_disk and not args.cache_text_encoder_outputs:
             args.cache_text_encoder_outputs = True
-            print(
+            logger.warning(
                 "cache_text_encoder_outputs is enabled because cache_text_encoder_outputs_to_disk is enabled / "
                 + "cache_text_encoder_outputs_to_diskが有効になっているためcache_text_encoder_outputsが有効になりました"
             )

library/slicing_vae.py

@@ -26,7 +26,10 @@ from diffusers.models.modeling_utils import ModelMixin
 from diffusers.models.unet_2d_blocks import UNetMidBlock2D, get_down_block, get_up_block
 from diffusers.models.vae import DecoderOutput, DiagonalGaussianDistribution
 from diffusers.models.autoencoder_kl import AutoencoderKLOutput
-
+from .utils import setup_logging
+setup_logging()
+import logging
+logger = logging.getLogger(__name__)
 
 def slice_h(x, num_slices):
     # slice with pad 1 both sides: to eliminate side effect of padding of conv2d
@@ -62,7 +65,7 @@ def cat_h(sliced):
     return x
 
 
-def resblock_forward(_self, num_slices, input_tensor, temb):
+def resblock_forward(_self, num_slices, input_tensor, temb, **kwargs):
     assert _self.upsample is None and _self.downsample is None
     assert _self.norm1.num_groups == _self.norm2.num_groups
     assert temb is None
@@ -89,7 +92,7 @@ def resblock_forward(_self, num_slices, input_tensor, temb):
     #     sliced_tensor = torch.chunk(x, num_div, dim=1)
     #     sliced_weight = torch.chunk(norm.weight, num_div, dim=0)
     #     sliced_bias = torch.chunk(norm.bias, num_div, dim=0)
-    #     print(sliced_tensor[0].shape, num_div, sliced_weight[0].shape, sliced_bias[0].shape)
+    #     logger.info(sliced_tensor[0].shape, num_div, sliced_weight[0].shape, sliced_bias[0].shape)
     #     normed_tensor = []
     #     for i in range(num_div):
     #         n = torch.group_norm(sliced_tensor[i], norm.num_groups, sliced_weight[i], sliced_bias[i], norm.eps)
@@ -243,7 +246,7 @@ class SlicingEncoder(nn.Module):
 
         self.num_slices = num_slices
         div = num_slices / (2 ** (len(self.down_blocks) - 1))  # 深い層はそこまで分割しなくていいので適宜減らす
-        # print(f"initial divisor: {div}")
+        # logger.info(f"initial divisor: {div}")
         if div >= 2:
             div = int(div)
             for resnet in self.mid_block.resnets:
@@ -253,11 +256,11 @@ class SlicingEncoder(nn.Module):
         for i, down_block in enumerate(self.down_blocks[::-1]):
             if div >= 2:
                 div = int(div)
-                # print(f"down block: {i} divisor: {div}")
+                # logger.info(f"down block: {i} divisor: {div}")
                 for resnet in down_block.resnets:
                     resnet.forward = wrapper(resblock_forward, resnet, div)
                 if down_block.downsamplers is not None:
-                    # print("has downsample")
+                    # logger.info("has downsample")
                     for downsample in down_block.downsamplers:
                         downsample.forward = wrapper(self.downsample_forward, downsample, div * 2)
             div *= 2
@@ -307,7 +310,7 @@ class SlicingEncoder(nn.Module):
     def downsample_forward(self, _self, num_slices, hidden_states):
         assert hidden_states.shape[1] == _self.channels
         assert _self.use_conv and _self.padding == 0
-        print("downsample forward", num_slices, hidden_states.shape)
+        logger.info(f"downsample forward {num_slices} {hidden_states.shape}")
 
         org_device = hidden_states.device
         cpu_device = torch.device("cpu")
@@ -350,7 +353,7 @@ class SlicingEncoder(nn.Module):
                 hidden_states = torch.cat([hidden_states, x], dim=2)
 
         hidden_states = hidden_states.to(org_device)
-        # print("downsample forward done", hidden_states.shape)
+        # logger.info(f"downsample forward done {hidden_states.shape}")
         return hidden_states
 
 
@@ -426,7 +429,7 @@ class SlicingDecoder(nn.Module):
 
         self.num_slices = num_slices
         div = num_slices / (2 ** (len(self.up_blocks) - 1))
-        print(f"initial divisor: {div}")
+        logger.info(f"initial divisor: {div}")
         if div >= 2:
             div = int(div)
             for resnet in self.mid_block.resnets:
@@ -436,11 +439,11 @@ class SlicingDecoder(nn.Module):
         for i, up_block in enumerate(self.up_blocks):
             if div >= 2:
                 div = int(div)
-                # print(f"up block: {i} divisor: {div}")
+                # logger.info(f"up block: {i} divisor: {div}")
                 for resnet in up_block.resnets:
                     resnet.forward = wrapper(resblock_forward, resnet, div)
                 if up_block.upsamplers is not None:
-                    # print("has upsample")
+                    # logger.info("has upsample")
                     for upsample in up_block.upsamplers:
                         upsample.forward = wrapper(self.upsample_forward, upsample, div * 2)
             div *= 2
@@ -528,7 +531,7 @@ class SlicingDecoder(nn.Module):
             del x
 
         hidden_states = torch.cat(sliced, dim=2)
-        # print("us hidden_states", hidden_states.shape)
+        # logger.info(f"us hidden_states {hidden_states.shape}")
         del sliced
 
         hidden_states = hidden_states.to(org_device)

library/utils.py

@@ -1,6 +1,266 @@
+import logging
+import sys
 import threading
+import torch
+from torchvision import transforms
 from typing import *
+from diffusers import EulerAncestralDiscreteScheduler
+import diffusers.schedulers.scheduling_euler_ancestral_discrete
+from diffusers.schedulers.scheduling_euler_ancestral_discrete import EulerAncestralDiscreteSchedulerOutput
 
 
 def fire_in_thread(f, *args, **kwargs):
-    threading.Thread(target=f, args=args, kwargs=kwargs).start()
+    threading.Thread(target=f, args=args, kwargs=kwargs).start()
+
+
+def add_logging_arguments(parser):
+    parser.add_argument(
+        "--console_log_level",
+        type=str,
+        default=None,
+        choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
+        help="Set the logging level, default is INFO / ログレベルを設定する。デフォルトはINFO",
+    )
+    parser.add_argument(
+        "--console_log_file",
+        type=str,
+        default=None,
+        help="Log to a file instead of stderr / 標準エラー出力ではなくファイルにログを出力する",
+    )
+    parser.add_argument("--console_log_simple", action="store_true", help="Simple log output / シンプルなログ出力")
+
+
+def setup_logging(args=None, log_level=None, reset=False):
+    if logging.root.handlers:
+        if reset:
+            # remove all handlers
+            for handler in logging.root.handlers[:]:
+                logging.root.removeHandler(handler)
+        else:
+            return
+
+    # log_level can be set by the caller or by the args, the caller has priority. If not set, use INFO
+    if log_level is None and args is not None:
+        log_level = args.console_log_level
+    if log_level is None:
+        log_level = "INFO"
+    log_level = getattr(logging, log_level)
+
+    msg_init = None
+    if args is not None and args.console_log_file:
+        handler = logging.FileHandler(args.console_log_file, mode="w")
+    else:
+        handler = None
+        if not args or not args.console_log_simple:
+            try:
+                from rich.logging import RichHandler
+                from rich.console import Console
+                from rich.logging import RichHandler
+
+                handler = RichHandler(console=Console(stderr=True))
+            except ImportError:
+                # print("rich is not installed, using basic logging")
+                msg_init = "rich is not installed, using basic logging"
+
+        if handler is None:
+            handler = logging.StreamHandler(sys.stdout)  # same as print
+            handler.propagate = False
+
+    formatter = logging.Formatter(
+        fmt="%(message)s",
+        datefmt="%Y-%m-%d %H:%M:%S",
+    )
+    handler.setFormatter(formatter)
+    logging.root.setLevel(log_level)
+    logging.root.addHandler(handler)
+
+    if msg_init is not None:
+        logger = logging.getLogger(__name__)
+        logger.info(msg_init)
+
+
+
+# TODO make inf_utils.py
+
+
+# region Gradual Latent hires fix
+
+
+class GradualLatent:
+    def __init__(
+        self,
+        ratio,
+        start_timesteps,
+        every_n_steps,
+        ratio_step,
+        s_noise=1.0,
+        gaussian_blur_ksize=None,
+        gaussian_blur_sigma=0.5,
+        gaussian_blur_strength=0.5,
+        unsharp_target_x=True,
+    ):
+        self.ratio = ratio
+        self.start_timesteps = start_timesteps
+        self.every_n_steps = every_n_steps
+        self.ratio_step = ratio_step
+        self.s_noise = s_noise
+        self.gaussian_blur_ksize = gaussian_blur_ksize
+        self.gaussian_blur_sigma = gaussian_blur_sigma
+        self.gaussian_blur_strength = gaussian_blur_strength
+        self.unsharp_target_x = unsharp_target_x
+
+    def __str__(self) -> str:
+        return (
+            f"GradualLatent(ratio={self.ratio}, start_timesteps={self.start_timesteps}, "
+            + f"every_n_steps={self.every_n_steps}, ratio_step={self.ratio_step}, s_noise={self.s_noise}, "
+            + f"gaussian_blur_ksize={self.gaussian_blur_ksize}, gaussian_blur_sigma={self.gaussian_blur_sigma}, gaussian_blur_strength={self.gaussian_blur_strength}, "
+            + f"unsharp_target_x={self.unsharp_target_x})"
+        )
+
+    def apply_unshark_mask(self, x: torch.Tensor):
+        if self.gaussian_blur_ksize is None:
+            return x
+        blurred = transforms.functional.gaussian_blur(x, self.gaussian_blur_ksize, self.gaussian_blur_sigma)
+        # mask = torch.sigmoid((x - blurred) * self.gaussian_blur_strength)
+        mask = (x - blurred) * self.gaussian_blur_strength
+        sharpened = x + mask
+        return sharpened
+
+    def interpolate(self, x: torch.Tensor, resized_size, unsharp=True):
+        org_dtype = x.dtype
+        if org_dtype == torch.bfloat16:
+            x = x.float()
+
+        x = torch.nn.functional.interpolate(x, size=resized_size, mode="bicubic", align_corners=False).to(dtype=org_dtype)
+
+        # apply unsharp mask / アンシャープマスクを適用する
+        if unsharp and self.gaussian_blur_ksize:
+            x = self.apply_unshark_mask(x)
+
+        return x
+
+
+class EulerAncestralDiscreteSchedulerGL(EulerAncestralDiscreteScheduler):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.resized_size = None
+        self.gradual_latent = None
+
+    def set_gradual_latent_params(self, size, gradual_latent: GradualLatent):
+        self.resized_size = size
+        self.gradual_latent = gradual_latent
+
+    def step(
+        self,
+        model_output: torch.FloatTensor,
+        timestep: Union[float, torch.FloatTensor],
+        sample: torch.FloatTensor,
+        generator: Optional[torch.Generator] = None,
+        return_dict: bool = True,
+    ) -> Union[EulerAncestralDiscreteSchedulerOutput, Tuple]:
+        """
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
+        process from the learned model outputs (most often the predicted noise).
+
+        Args:
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            timestep (`float`):
+                The current discrete timestep in the diffusion chain.
+            sample (`torch.FloatTensor`):
+                A current instance of a sample created by the diffusion process.
+            generator (`torch.Generator`, *optional*):
+                A random number generator.
+            return_dict (`bool`):
+                Whether or not to return a
+                [`~schedulers.scheduling_euler_ancestral_discrete.EulerAncestralDiscreteSchedulerOutput`] or tuple.
+
+        Returns:
+            [`~schedulers.scheduling_euler_ancestral_discrete.EulerAncestralDiscreteSchedulerOutput`] or `tuple`:
+                If return_dict is `True`,
+                [`~schedulers.scheduling_euler_ancestral_discrete.EulerAncestralDiscreteSchedulerOutput`] is returned,
+                otherwise a tuple is returned where the first element is the sample tensor.
+
+        """
+
+        if isinstance(timestep, int) or isinstance(timestep, torch.IntTensor) or isinstance(timestep, torch.LongTensor):
+            raise ValueError(
+                (
+                    "Passing integer indices (e.g. from `enumerate(timesteps)`) as timesteps to"
+                    " `EulerDiscreteScheduler.step()` is not supported. Make sure to pass"
+                    " one of the `scheduler.timesteps` as a timestep."
+                ),
+            )
+
+        if not self.is_scale_input_called:
+            # logger.warning(
+            print(
+                "The `scale_model_input` function should be called before `step` to ensure correct denoising. "
+                "See `StableDiffusionPipeline` for a usage example."
+            )
+
+        if self.step_index is None:
+            self._init_step_index(timestep)
+
+        sigma = self.sigmas[self.step_index]
+
+        # 1. compute predicted original sample (x_0) from sigma-scaled predicted noise
+        if self.config.prediction_type == "epsilon":
+            pred_original_sample = sample - sigma * model_output
+        elif self.config.prediction_type == "v_prediction":
+            # * c_out + input * c_skip
+            pred_original_sample = model_output * (-sigma / (sigma**2 + 1) ** 0.5) + (sample / (sigma**2 + 1))
+        elif self.config.prediction_type == "sample":
+            raise NotImplementedError("prediction_type not implemented yet: sample")
+        else:
+            raise ValueError(f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, or `v_prediction`")
+
+        sigma_from = self.sigmas[self.step_index]
+        sigma_to = self.sigmas[self.step_index + 1]
+        sigma_up = (sigma_to**2 * (sigma_from**2 - sigma_to**2) / sigma_from**2) ** 0.5
+        sigma_down = (sigma_to**2 - sigma_up**2) ** 0.5
+
+        # 2. Convert to an ODE derivative
+        derivative = (sample - pred_original_sample) / sigma
+
+        dt = sigma_down - sigma
+
+        device = model_output.device
+        if self.resized_size is None:
+            prev_sample = sample + derivative * dt
+
+            noise = diffusers.schedulers.scheduling_euler_ancestral_discrete.randn_tensor(
+                model_output.shape, dtype=model_output.dtype, device=device, generator=generator
+            )
+            s_noise = 1.0
+        else:
+            print("resized_size", self.resized_size, "model_output.shape", model_output.shape, "sample.shape", sample.shape)
+            s_noise = self.gradual_latent.s_noise
+
+            if self.gradual_latent.unsharp_target_x:
+                prev_sample = sample + derivative * dt
+                prev_sample = self.gradual_latent.interpolate(prev_sample, self.resized_size)
+            else:
+                sample = self.gradual_latent.interpolate(sample, self.resized_size)
+                derivative = self.gradual_latent.interpolate(derivative, self.resized_size, unsharp=False)
+                prev_sample = sample + derivative * dt
+
+            noise = diffusers.schedulers.scheduling_euler_ancestral_discrete.randn_tensor(
+                (model_output.shape[0], model_output.shape[1], self.resized_size[0], self.resized_size[1]),
+                dtype=model_output.dtype,
+                device=device,
+                generator=generator,
+            )
+
+        prev_sample = prev_sample + noise * sigma_up * s_noise
+
+        # upon completion increase step index by one
+        self._step_index += 1
+
+        if not return_dict:
+            return (prev_sample,)
+
+        return EulerAncestralDiscreteSchedulerOutput(prev_sample=prev_sample, pred_original_sample=pred_original_sample)
+
+
+# endregion