Update app.py

app.py

@@ -53,64 +53,64 @@ transformer_path = "Kunbyte/ROSE"
 config_path = "./configs/wan2.1/wan_civitai.yaml"
 config = OmegaConf.load(config_path)
 
-repo_id = "alibaba-pai/Wan2.1-Fun-1.3B-InP"
+# repo_id = "alibaba-pai/Wan2.1-Fun-1.3B-InP"
 
-text_encoder_path = download_component_subfolder(repo_id, config['text_encoder_kwargs'].get('text_encoder_subpath', 'text_encoder'))
-tokenizer_path = download_component_subfolder(repo_id, config['text_encoder_kwargs'].get('tokenizer_subpath', 'tokenizer'))
-image_encoder_path = download_component_subfolder(repo_id, config['image_encoder_kwargs'].get('image_encoder_subpath', 'image_encoder'))
-vae_path = download_component_subfolder(repo_id, config['vae_kwargs'].get('vae_subpath', 'vae'))
+# text_encoder_path = download_component_subfolder(repo_id, config['text_encoder_kwargs'].get('text_encoder_subpath', 'text_encoder'))
+# tokenizer_path = download_component_subfolder(repo_id, config['text_encoder_kwargs'].get('tokenizer_subpath', 'tokenizer'))
+# image_encoder_path = download_component_subfolder(repo_id, config['image_encoder_kwargs'].get('image_encoder_subpath', 'image_encoder'))
+# vae_path = download_component_subfolder(repo_id, config['vae_kwargs'].get('vae_subpath', 'vae'))
 
-tokenizer = AutoTokenizer.from_pretrained(tokenizer_path)
+# tokenizer = AutoTokenizer.from_pretrained(tokenizer_path)
 
-text_encoder = WanT5EncoderModel.from_pretrained(
-    text_encoder_path,
-    additional_kwargs=OmegaConf.to_container(config['text_encoder_kwargs']),
-    low_cpu_mem_usage=False,
-    torch_dtype=torch.bfloat16
-)
-
-clip_image_encoder = CLIPModel.from_pretrained(image_encoder_path)
-
-vae = AutoencoderKLWan.from_pretrained(
-    vae_path,
-    additional_kwargs=OmegaConf.to_container(config['vae_kwargs']),
-)
-
-transformer_subpath = config['transformer_additional_kwargs'].get('transformer_subpath', 'transformer')
-transformer3d = WanTransformer3DModel.from_pretrained(
-    transformer_path,
-    subfolder=transformer_subpath,
-    transformer_additional_kwargs=OmegaConf.to_container(config['transformer_additional_kwargs']),
-)
-
-noise_scheduler = FlowMatchEulerDiscreteScheduler(
-    **filter_kwargs(FlowMatchEulerDiscreteScheduler, OmegaConf.to_container(config['scheduler_kwargs']))
-)
-
-
-# tokenizer = AutoTokenizer.from_pretrained(
-#     os.path.join(pretrained_model_path, config['text_encoder_kwargs'].get('tokenizer_subpath', 'tokenizer')),
-# )
 # text_encoder = WanT5EncoderModel.from_pretrained(
-#     os.path.join(pretrained_model_path, config['text_encoder_kwargs'].get('text_encoder_subpath', 'text_encoder')),
+#     text_encoder_path,
 #     additional_kwargs=OmegaConf.to_container(config['text_encoder_kwargs']),
-#     low_cpu_mem_usage=True,
-# )
-# clip_image_encoder = CLIPModel.from_pretrained(
-#     os.path.join(pretrained_model_path, config['image_encoder_kwargs'].get('image_encoder_subpath', 'image_encoder')),
+#     low_cpu_mem_usage=False,
+#     torch_dtype=torch.bfloat16
 # )
+
+# clip_image_encoder = CLIPModel.from_pretrained(image_encoder_path)
+
 # vae = AutoencoderKLWan.from_pretrained(
-#     os.path.join(pretrained_model_path, config['vae_kwargs'].get('vae_subpath', 'vae')),
+#     vae_path,
 #     additional_kwargs=OmegaConf.to_container(config['vae_kwargs']),
 # )
+
+# transformer_subpath = config['transformer_additional_kwargs'].get('transformer_subpath', 'transformer')
 # transformer3d = WanTransformer3DModel.from_pretrained(
-#     os.path.join(transformer_path, config['transformer_additional_kwargs'].get('transformer_subpath', 'transformer')),
+#     transformer_path,
+#     subfolder=transformer_subpath,
 #     transformer_additional_kwargs=OmegaConf.to_container(config['transformer_additional_kwargs']),
 # )
+
 # noise_scheduler = FlowMatchEulerDiscreteScheduler(
 #     **filter_kwargs(FlowMatchEulerDiscreteScheduler, OmegaConf.to_container(config['scheduler_kwargs']))
 # )
 
+
+tokenizer = AutoTokenizer.from_pretrained(
+    os.path.join(pretrained_model_path, config['text_encoder_kwargs'].get('tokenizer_subpath', 'tokenizer')),
+)
+text_encoder = WanT5EncoderModel.from_pretrained(
+    os.path.join(pretrained_model_path, config['text_encoder_kwargs'].get('text_encoder_subpath', 'text_encoder')),
+    additional_kwargs=OmegaConf.to_container(config['text_encoder_kwargs']),
+    low_cpu_mem_usage=True,
+)
+clip_image_encoder = CLIPModel.from_pretrained(
+    os.path.join(pretrained_model_path, config['image_encoder_kwargs'].get('image_encoder_subpath', 'image_encoder')),
+)
+vae = AutoencoderKLWan.from_pretrained(
+    os.path.join(pretrained_model_path, config['vae_kwargs'].get('vae_subpath', 'vae')),
+    additional_kwargs=OmegaConf.to_container(config['vae_kwargs']),
+)
+transformer3d = WanTransformer3DModel.from_pretrained(
+    os.path.join(transformer_path, config['transformer_additional_kwargs'].get('transformer_subpath', 'transformer')),
+    transformer_additional_kwargs=OmegaConf.to_container(config['transformer_additional_kwargs']),
+)
+noise_scheduler = FlowMatchEulerDiscreteScheduler(
+    **filter_kwargs(FlowMatchEulerDiscreteScheduler, OmegaConf.to_container(config['scheduler_kwargs']))
+)
+
 pipeline = WanFunInpaintPipeline(
     vae=vae,
     text_encoder=text_encoder,