Update app.py

app.py

@@ -216,11 +216,11 @@ def load_models():
         
         # 加载模型
         try:
-            text_encoder = LlamaModel.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder='text_encoder', torch_dtype=dtype).to(model_device)
-            text_encoder_2 = CLIPTextModel.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder='text_encoder_2', torch_dtype=dtype).to(model_device)
-            tokenizer = LlamaTokenizerFast.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder='tokenizer')
-            tokenizer_2 = CLIPTokenizer.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder='tokenizer_2')
-            vae = AutoencoderKLHunyuanVideo.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder='vae', torch_dtype=dtype).to(model_device)
+            text_encoder = LlamaModel.from_pretrained("hunyuanvideo-community/HunyuanVideo-I2V", subfolder='text_encoder', torch_dtype=dtype).to(model_device)
+            text_encoder_2 = CLIPTextModel.from_pretrained("hunyuanvideo-community/HunyuanVideo-I2V", subfolder='text_encoder_2', torch_dtype=dtype).to(model_device)
+            tokenizer = LlamaTokenizerFast.from_pretrained("hunyuanvideo-community/HunyuanVideo-I2V", subfolder='tokenizer')
+            tokenizer_2 = CLIPTokenizer.from_pretrained("hunyuanvideo-community/HunyuanVideo-I2V", subfolder='tokenizer_2')
+            vae = AutoencoderKLHunyuanVideo.from_pretrained("hunyuanvideo-community/HunyuanVideo-I2V", subfolder='vae', torch_dtype=dtype).to(model_device)
 
             feature_extractor = SiglipImageProcessor.from_pretrained("lllyasviel/flux_redux_bfl", subfolder='feature_extractor')
             image_encoder = SiglipVisionModel.from_pretrained("lllyasviel/flux_redux_bfl", subfolder='image_encoder', torch_dtype=dtype).to(model_device)
@@ -237,11 +237,11 @@ def load_models():
             transformer_dtype = torch.float32
             cpu_fallback_mode = True
             
-            text_encoder = LlamaModel.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder='text_encoder', torch_dtype=dtype).to('cpu')
-            text_encoder_2 = CLIPTextModel.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder='text_encoder_2', torch_dtype=dtype).to('cpu')
-            tokenizer = LlamaTokenizerFast.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder='tokenizer')
-            tokenizer_2 = CLIPTokenizer.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder='tokenizer_2')
-            vae = AutoencoderKLHunyuanVideo.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder='vae', torch_dtype=dtype).to('cpu')
+            text_encoder = LlamaModel.from_pretrained("hunyuanvideo-community/HunyuanVideo-I2VHunyuanVideo-I2VHunyuanVideo-I2VHunyuanVideo-I2VHunyuanVideo-I2V", subfolder='text_encoder', torch_dtype=dtype).to('cpu')
+            text_encoder_2 = CLIPTextModel.from_pretrained("hunyuanvideo-community/HunyuanVideo-I2VHunyuanVideo-I2VHunyuanVideo-I2VHunyuanVideo-I2V", subfolder='text_encoder_2', torch_dtype=dtype).to('cpu')
+            tokenizer = LlamaTokenizerFast.from_pretrained("hunyuanvideo-community/HunyuanVideo-I2VHunyuanVideo-I2VHunyuanVideo-I2V", subfolder='tokenizer')
+            tokenizer_2 = CLIPTokenizer.from_pretrained("hunyuanvideo-community/HunyuanVideo-I2VHunyuanVideo-I2V", subfolder='tokenizer_2')
+            vae = AutoencoderKLHunyuanVideo.from_pretrained("hunyuanvideo-community/HunyuanVideo-I2V", subfolder='vae', torch_dtype=dtype).to('cpu')
 
             feature_extractor = SiglipImageProcessor.from_pretrained("lllyasviel/flux_redux_bfl", subfolder='feature_extractor')
             image_encoder = SiglipVisionModel.from_pretrained("lllyasviel/flux_redux_bfl", subfolder='image_encoder', torch_dtype=dtype).to('cpu')