fix load error & update readme

README.md

@@ -158,7 +158,7 @@ import torch
 from diffusers import AutoencoderKLWan, WanImageToVideoPipeline
 from diffusers.utils import export_to_video, load_image
 
-# Available models: Wan-AI/Wan2.1-I2V-14B-480P-Diffusers, Wan-AI/Wan2.1-I2V-1.3B-720P-Diffusers
+# Available models: Wan-AI/Wan2.1-I2V-14B-480P-Diffusers, Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
 model_id = "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers"
 vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
 pipe = WanImageToVideoPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
@@ -177,7 +177,7 @@ negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles
 output = pipe(
     image=image, prompt=prompt, negative_prompt=negative_prompt, num_frames=81, guidance_scale=5.0
 ).frames[0]
-export_to_video(output, "output.mp4", fps=15)
+export_to_video(output, "output.mp4", fps=16)
 ```
 
 ##### (2) Using Prompt Extention

image_processor/preprocessor_config.json

@@ -19,7 +19,6 @@
     0.26130258,
     0.27577711
   ],
-  "processor_class": "CLIPProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {

image_processor/special_tokens_map.json

@@ -1,30 +0,0 @@
-{
-  "bos_token": {
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

image_processor/tokenizer_config.json

@@ -1,32 +0,0 @@
-{
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "49406": {
-      "content": "<|startoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49407": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|startoftext|>",
-  "clean_up_tokenization_spaces": false,
-  "do_lower_case": true,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 77,
-  "pad_token": "<|endoftext|>",
-  "processor_class": "CLIPProcessor",
-  "tokenizer_class": "CLIPTokenizer",
-  "unk_token": "<|endoftext|>"
-}

model_index.json

@@ -7,7 +7,7 @@
   ],
   "image_processor": [
     "transformers",
-    "CLIPProcessor"
+    "CLIPImageProcessor"
   ],
   "scheduler": [
     "diffusers",