Merge branch 'dev' into deep-speed

library/train_util.py

@@ -2937,7 +2937,12 @@ def add_training_arguments(parser: argparse.ArgumentParser, support_dreambooth:
     parser.add_argument(
         "--save_state",
         action="store_true",
-        help="save training state additionally (including optimizer states etc.) / optimizerなど学習状態も含めたstateを追加で保存する",
+        help="save training state additionally (including optimizer states etc.) when saving model / optimizerなど学習状態も含めたstateをモデル保存時に追加で保存する",
+    )
+    parser.add_argument(
+        "--save_state_on_train_end",
+        action="store_true",
+        help="save training state (including optimizer states etc.) on train end / optimizerなど学習状態も含めたstateを学習完了時に保存する",
     )
     parser.add_argument("--resume", type=str, default=None, help="saved state to resume training / 学習再開するモデルのstate")
 
@@ -3088,6 +3093,11 @@ def add_training_arguments(parser: argparse.ArgumentParser, support_dreambooth:
         default=None,
         help="enable noise offset with this value (if enabled, around 0.1 is recommended) / Noise offsetを有効にしてこの値を設定する（有効にする場合は0.1程度を推奨）",
     )
+    parser.add_argument(
+        "--noise_offset_random_strength",
+        action="store_true",
+        help="use random strength between 0~noise_offset for noise offset. / noise offsetにおいて、0からnoise_offsetの間でランダムな強度を使用します。",
+    )
     parser.add_argument(
         "--multires_noise_iterations",
         type=int,
@@ -3101,6 +3111,12 @@ def add_training_arguments(parser: argparse.ArgumentParser, support_dreambooth:
         help="enable input perturbation noise. used for regularization. recommended value: around 0.1 (from arxiv.org/abs/2301.11706) "
         + "/  input perturbation noiseを有効にする。正則化に使用される。推奨値: 0.1程度 (arxiv.org/abs/2301.11706 より)",
     )
+    parser.add_argument(
+        "--ip_noise_gamma_random_strength",
+        action="store_true",
+        help="Use random strength between 0~ip_noise_gamma for input perturbation noise."
+        + "/ input perturbation noiseにおいて、0からip_noise_gammaの間でランダムな強度を使用します。",
+    )
     # parser.add_argument(
     #     "--perlin_noise",
     #     type=int,
@@ -3535,7 +3551,7 @@ def read_config_from_file(args: argparse.Namespace, parser: argparse.ArgumentPar
         exit(1)
 
     logger.info(f"Loading settings from {config_path}...")
-    with open(config_path, "r") as f:
+    with open(config_path, "r", encoding="utf-8") as f:
         config_dict = toml.load(f)
 
     # combine all sections into one
@@ -4661,7 +4677,11 @@ def get_noise_noisy_latents_and_timesteps(args, noise_scheduler, latents):
     # Sample noise that we'll add to the latents
     noise = torch.randn_like(latents, device=latents.device)
     if args.noise_offset:
-        noise = custom_train_functions.apply_noise_offset(latents, noise, args.noise_offset, args.adaptive_noise_scale)
+        if args.noise_offset_random_strength:
+            noise_offset = torch.rand(1, device=latents.device) * args.noise_offset
+        else:
+            noise_offset = args.noise_offset
+        noise = custom_train_functions.apply_noise_offset(latents, noise, noise_offset, args.adaptive_noise_scale)
     if args.multires_noise_iterations:
         noise = custom_train_functions.pyramid_noise_like(
             noise, latents.device, args.multires_noise_iterations, args.multires_noise_discount
@@ -4678,7 +4698,11 @@ def get_noise_noisy_latents_and_timesteps(args, noise_scheduler, latents):
     # Add noise to the latents according to the noise magnitude at each timestep
     # (this is the forward diffusion process)
     if args.ip_noise_gamma:
-        noisy_latents = noise_scheduler.add_noise(latents, noise + args.ip_noise_gamma * torch.randn_like(latents), timesteps)
+        if args.ip_noise_gamma_random_strength:
+            strength = torch.rand(1, device=latents.device) * args.ip_noise_gamma
+        else:
+            strength = args.ip_noise_gamma
+        noisy_latents = noise_scheduler.add_noise(latents, noise + strength * torch.randn_like(latents), timesteps)
     else:
         noisy_latents = noise_scheduler.add_noise(latents, noise, timesteps)