update demo (#6)

- fix load error & update readme (3cb3d96865bbe334ac52f981b3b437333b0eabed)
- update readme (c7c741dcdbce91016f160a1907332bf757a3e89a)


Co-authored-by: sypyp <[email protected]>

README.md

@@ -155,19 +155,27 @@ Wan can also be run directly using 🤗 Diffusers!
 
 ```python
 import torch
+import numpy as np
 from diffusers import AutoencoderKLWan, WanImageToVideoPipeline
 from diffusers.utils import export_to_video, load_image
+from transformers import CLIPVisionModel
 
-# 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"
+image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float32)
 vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
-pipe = WanImageToVideoPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
+pipe = WanImageToVideoPipeline.from_pretrained(model_id, vae=vae, image_encoder=image_encoder, torch_dtype=torch.bfloat16)
 pipe.to("cuda")
 
-height, width = 480, 832
 image = load_image(
     "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
-).resize((width, height))
+)
+max_area = 480 * 832
+aspect_ratio = image.height / image.width
+mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
+height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
+width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
+image = image.resize((width, height))
 prompt = (
     "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in "
     "the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."
@@ -175,9 +183,9 @@ prompt = (
 negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
 
 output = pipe(
-    image=image, prompt=prompt, negative_prompt=negative_prompt, num_frames=81, guidance_scale=5.0
+    image=image, prompt=prompt, negative_prompt=negative_prompt, height=height, width=width, 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_encoder/config.json

@@ -18,6 +18,6 @@
   "num_hidden_layers": 32,
   "patch_size": 14,
   "projection_dim": 1024,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.48.0.dev0"
 }

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",