Merge pull request #1020 from kohya-ss/dev

Fix convert_diffusers20_original_sd.py and add metadata & variant options

README.md

@@ -249,6 +249,13 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
 
 ## Change History
 
+### Dec 24, 2023 / 2023/12/24
+
+- Fixed to work `tools/convert_diffusers20_original_sd.py`. Thanks to Disty0! PR [#1016](https://github.com/kohya-ss/sd-scripts/pull/1016)
+
+- `tools/convert_diffusers20_original_sd.py` が動かなくなっていたのが修正されました。Disty0 氏に感謝します。 PR [#1016](https://github.com/kohya-ss/sd-scripts/pull/1016) 
+
+
 ### Dec 21, 2023 / 2023/12/21
 
 - The issues in multi-GPU training are fixed. Thanks to Isotr0py! PR [#989](https://github.com/kohya-ss/sd-scripts/pull/989) and [#1000](https://github.com/kohya-ss/sd-scripts/pull/1000)

tools/convert_diffusers20_original_sd.py

@@ -23,7 +23,7 @@ def convert(args):
     is_load_ckpt = os.path.isfile(args.model_to_load)
     is_save_ckpt = len(os.path.splitext(args.model_to_save)[1]) > 0
 
-    assert not is_load_ckpt or args.v1 != args.v2, f"v1 or v2 is required to load checkpoint / checkpointの読み込みにはv1/v2指定が必要です"
+    assert not is_load_ckpt or args.v1 != args.v2, "v1 or v2 is required to load checkpoint / checkpointの読み込みにはv1/v2指定が必要です"
     # assert (
     #     is_save_ckpt or args.reference_model is not None
     # ), f"reference model is required to save as Diffusers / Diffusers形式での保存には参照モデルが必要です"
@@ -34,10 +34,12 @@ def convert(args):
 
     if is_load_ckpt:
         v2_model = args.v2
-        text_encoder, vae, unet = model_util.load_models_from_stable_diffusion_checkpoint(v2_model, args.model_to_load, unet_use_linear_projection_in_v2=args.unet_use_linear_projection)
+        text_encoder, vae, unet = model_util.load_models_from_stable_diffusion_checkpoint(
+            v2_model, args.model_to_load, unet_use_linear_projection_in_v2=args.unet_use_linear_projection
+        )
     else:
         pipe = StableDiffusionPipeline.from_pretrained(
-            args.model_to_load, torch_dtype=load_dtype, tokenizer=None, safety_checker=None
+            args.model_to_load, torch_dtype=load_dtype, tokenizer=None, safety_checker=None, variant=args.variant
         )
         text_encoder = pipe.text_encoder
         vae = pipe.vae
@@ -57,15 +59,26 @@ def convert(args):
     if is_save_ckpt:
         original_model = args.model_to_load if is_load_ckpt else None
         key_count = model_util.save_stable_diffusion_checkpoint(
-            v2_model, args.model_to_save, text_encoder, unet, original_model, args.epoch, args.global_step, save_dtype, vae
+            v2_model,
+            args.model_to_save,
+            text_encoder,
+            unet,
+            original_model,
+            args.epoch,
+            args.global_step,
+            None if args.metadata is None else eval(args.metadata),
+            save_dtype=save_dtype,
+            vae=vae,
         )
         print(f"model saved. total converted state_dict keys: {key_count}")
     else:
-        print(f"copy scheduler/tokenizer config from: {args.reference_model if args.reference_model is not None else 'default model'}")
+        print(
+            f"copy scheduler/tokenizer config from: {args.reference_model if args.reference_model is not None else 'default model'}"
+        )
         model_util.save_diffusers_checkpoint(
             v2_model, args.model_to_save, text_encoder, unet, args.reference_model, vae, args.use_safetensors
         )
-        print(f"model saved.")
+        print("model saved.")
 
 
 def setup_parser() -> argparse.ArgumentParser:
@@ -77,7 +90,9 @@ def setup_parser() -> argparse.ArgumentParser:
         "--v2", action="store_true", help="load v2.0 model (v1 or v2 is required to load checkpoint) / 2.0のモデルを読み込む"
     )
     parser.add_argument(
-        "--unet_use_linear_projection", action="store_true", help="When saving v2 model as Diffusers, set U-Net config to `use_linear_projection=true` (to match stabilityai's model) / Diffusers形式でv2モデルを保存するときにU-Netの設定を`use_linear_projection=true`にする（stabilityaiのモデルと合わせる）"
+        "--unet_use_linear_projection",
+        action="store_true",
+        help="When saving v2 model as Diffusers, set U-Net config to `use_linear_projection=true` (to match stabilityai's model) / Diffusers形式でv2モデルを保存するときにU-Netの設定を`use_linear_projection=true`にする（stabilityaiのモデルと合わせる）",
     )
     parser.add_argument(
         "--fp16",
@@ -99,6 +114,18 @@ def setup_parser() -> argparse.ArgumentParser:
     parser.add_argument(
         "--global_step", type=int, default=0, help="global_step to write to checkpoint / checkpointに記録するglobal_stepの値"
     )
+    parser.add_argument(
+        "--metadata",
+        type=str,
+        default=None,
+        help='モデルに保存されるメタデータ、Pythonの辞書形式で指定 / metadata: metadata written in to the model in Python Dictionary. Example metadata: \'{"name": "model_name", "resolution": "512x512"}\'',
+    )
+    parser.add_argument(
+        "--variant",
+        type=str,
+        default=None,
+        help="読む込むDiffusersのvariantを指定する、例: fp16 / variant: Diffusers variant to load. Example: fp16",
+    )
     parser.add_argument(
         "--reference_model",
         type=str,