update

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/mix/1/1.jpeg filter=lfs diff=lfs merge=lfs -text
+examples/mix/1/1.mp4 filter=lfs diff=lfs merge=lfs -text
+examples/mix/2/2.jpeg filter=lfs diff=lfs merge=lfs -text
+examples/mix/2/2.mp4 filter=lfs diff=lfs merge=lfs -text
+examples/mov/1/1.jpeg filter=lfs diff=lfs merge=lfs -text
+examples/mov/1/1.mp4 filter=lfs diff=lfs merge=lfs -text
+examples/mov/2/2.jpeg filter=lfs diff=lfs merge=lfs -text
+examples/mov/2/2.mp4 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -8,7 +8,6 @@ import time
 import gradio as gr
 import requests
 
-os.system("pip install dashscope")
 import dashscope
 from dashscope.utils.oss_utils import check_and_upload_local
 
@@ -112,11 +111,121 @@ def start_app():
 
     with gr.Blocks(title="Wan2.2-Animate 视频生成") as demo:
         gr.HTML("""
-            <div style="text-align: center; font-size: 32px; font-weight: bold; margin-bottom: 20px;">
-                Wan2.2-Animate
+
+            
+            <div style="padding: 2rem; text-align: center; max-width: 1200px; margin: 0 auto; font-family: Arial, sans-serif;">
+
+                <h1 style="font-size: 2.5rem; font-weight: bold; margin-bottom: 0.5rem; color: #333;">
+                    Wan2.2-Animate: Unified Character Animation and Replacement with Holistic Replication
+                </h1>
+                
+                <h3 style="font-size: 2.5rem; font-weight: bold; margin-bottom: 0.5rem; color: #333;">
+                    Wan2.2-Animate: 统一的角色动画和视频人物替换模型
+                </h3>
+
+                <div style="font-size: 1.25rem; margin-bottom: 1.5rem; color: #555;">
+                    Tongyi Lab, Alibaba
+                </div>
+
+                <div style="display: flex; flex-wrap: wrap; justify-content: center; gap: 1rem; margin-bottom: 1rem;">
+                    <!-- 第一行按钮 -->
+                    <a href="https://arxiv.org/abs/2509.14055" target="_blank"
+                    style="display: inline-flex; align-items: center; padding: 0.5rem 1rem; background-color: #f0f0f0; /* 浅灰色背景 */ color: #333; /* 深色文字 */ text-decoration: none; border-radius: 9999px; font-weight: 500; transition: background-color 0.3s;">
+                        <span style="margin-right: 0.5rem;">📄</span> <!-- 使用文档图标 -->
+                        <span>Paper</span>
+                    </a>
+
+                    <a href="https://github.com/Wan-Video/Wan2.2" target="_blank"
+                    style="display: inline-flex; align-items: center; padding: 0.5rem 1rem; background-color: #f0f0f0; color: #333; text-decoration: none; border-radius: 9999px; font-weight: 500; transition: background-color 0.3s;">
+                        <span style="margin-right: 0.5rem;">💻</span> <!-- 使用电脑图标 -->
+                        <span>GitHub</span>
+                    </a>
+
+                    <a href="https://huggingface.co/Wan-AI/Wan2.2-Animate-14B" target="_blank"
+                    style="display: inline-flex; align-items: center; padding: 0.5rem 1rem; background-color: #f0f0f0; color: #333; text-decoration: none; border-radius: 9999px; font-weight: 500; transition: background-color 0.3s;">
+                        <span style="margin-right: 0.5rem;">🤗</span>
+                        <span>HF Model</span>
+                    </a>
+
+                    <a href="https://www.modelscope.cn/models/Wan-AI/Wan2.2-Animate-14B" target="_blank"
+                    style="display: inline-flex; align-items: center; padding: 0.5rem 1rem; background-color: #f0f0f0; color: #333; text-decoration: none; border-radius: 9999px; font-weight: 500; transition: background-color 0.3s;">
+                        <span style="margin-right: 0.5rem;">🤖</span>
+                        <span>MS Model</span>
+                    </a>
+                </div>
+
+                <div style="display: flex; flex-wrap: wrap; justify-content: center; gap: 1rem;">
+                    <!-- 第二行按钮 -->
+                    <a href="https://huggingface.co/spaces/Wan-AI/Wan2.2-Animate" target="_blank"
+                    style="display: inline-flex; align-items: center; padding: 0.5rem 1rem; background-color: #f0f0f0; color: #333; text-decoration: none; border-radius: 9999px; font-weight: 500; transition: background-color 0.3s;">
+                        <span style="margin-right: 0.5rem;">🤗</span>
+                        <span>HF Space</span>
+                    </a>
+
+                    <a href="https://www.modelscope.cn/studios/Wan-AI/Wan2.2-Animate" target="_blank"
+                    style="display: inline-flex; align-items: center; padding: 0.5rem 1rem; background-color: #f0f0f0; color: #333; text-decoration: none; border-radius: 9999px; font-weight: 500; transition: background-color 0.3s;">
+                        <span style="margin-right: 0.5rem;">🤖</span>
+                        <span>MS Studio</span>
+                    </a>
+                </div>
+
             </div>
+            
             """)
-        gr.Markdown("基于参考图像和骨骼序列的人物驱动和替换视频生成")
+        
+        gr.HTML("""
+                <details>
+                    <summary>‼️Usage (使用说明)</summary>
+                    
+                    Wan-Animate supports two mode:
+                    <ul>
+                        <li>Move Mode: animate the  character in input image with movements from the input video</li>
+                        <li>Mix Mode: replace the character in input video with the character in input image</li>
+                    </ul>
+                    
+                    Wan-Animate 支持两种模式:
+                    <ul>
+                        <li>Move模式: 用输入视频中提取的动作，驱动输入图片中的角色</li>
+                        <li>Mix模式: 用输入图片中的角色，替换输入视频中的角色</li>
+                    </ul>
+
+                    Currently, the following restrictions apply to inputs:
+
+                    <ul> <li>Video file size: Less than 200MB</li> 
+                    <li>Video resolution: The shorter side must be greater than 200, and the longer side must be less than 2048</li> 
+                    <li>Video duration: 2s to 30s</li> 
+                    <li>Video aspect ratio: 1:3 to 3:1</li> 
+                    <li>Video formats: mp4, avi, mov</li> 
+                    <li>Image file size: Less than 5MB</li> 
+                    <li>Image resolution: The shorter side must be greater than 200, and the longer side must be less than 4096</li> 
+                    <li>Image formats: jpg, png, jpeg, webp, bmp</li> </ul>
+
+                    
+                    当前，对于输入有以下的限制 
+
+                    <ul>
+                        <li>视频文件大小: 小于 200MB</li>
+                        <li>视频分辨率： 最小边大于 200, 最大边小于2048</li>
+                        <li>视频时长: 2s ~ 30s </li> 
+                        <li>视频比例：1:3 ~ 3:1 </li>
+                        <li>视频格式: mp4, avi, mov </li> 
+                        <li>图片文件大小: 小于5MB </li>
+                        <li>图片分辨率：最小边大于200，最大边小于4096 </li>
+                        <li>图片格式: jpg, png, jpeg, webp, bmp </li> 
+                    </ul>     
+                    
+                    <p> Currently, the inference quality has two variants. You can use our open-source code for more flexible configuration. </p>
+                    
+                    <p>当前，推理质量有两个变种。 您可以使用我们的开源代码，来进行更灵活的设置。</p>
+                    
+                    <ul>
+                        <li> wan-pro: 25fps, 720p </li> 
+                        <li> wan-std: 15fps, 720p  </li>
+                    </ul>     
+                              
+
+                </details>                
+                """)
 
         with gr.Row():
             with gr.Column():    
@@ -133,24 +242,23 @@ def start_app():
                 
                 with gr.Row():
                     model_id = gr.Dropdown(
-                        label="模型名称",
+                        label="Mode(模式)",
                         choices=["wan2.2-animate-move", "wan2.2-animate-mix"],
                         value="wan2.2-animate-move",
-                        info="支持mov和mix模型"
+                        info=""
                     )
 
                     model = gr.Dropdown(
-                        label="模式",
+                        label="推理质量(Inference Quality)",
                         choices=["wan-pro", "wan-std"],
                         value="wan-pro",
-                        info="支持标准模型std和专业模式pro两个版本"
                     )
 
                 run_button = gr.Button("Generate Video(生成视频)")
 
             with gr.Column():
                 output_video = gr.Video(label="Output Video(输出视频)")
-                output_status = gr.Textbox(label="Status")
+                output_status = gr.Textbox(label="Status(状态)")
         
         run_button.click(
             fn=app.predict,
@@ -163,42 +271,26 @@ def start_app():
             outputs=[output_video, output_status],
         )
 
-        # examples_dir = "examples"
-        # if os.path.exists(examples_dir):
-        #     example_data = []
-            
-        #     files_dict = {}
-        #     for file in os.listdir(examples_dir):
-        #         file_path = os.path.join(examples_dir, file)
-        #         name, ext = os.path.splitext(file)
-                
-        #         if ext.lower() in [".png", ".jpg", ".jpeg", ".bmp", ".tiff", ".webp"]:
-        #             if name not in files_dict:
-        #                 files_dict[name] = {}
-        #             files_dict[name]["image"] = file_path
-        #         elif ext.lower() in [".mp3", ".wav"]:
-        #             if name not in files_dict:
-        #                 files_dict[name] = {}
-        #             files_dict[name]["audio"] = file_path
-            
-        #     for name, files in files_dict.items():
-        #         if "image" in files and "audio" in files:
-        #             example_data.append([
-        #                 files["image"], 
-        #                 files["audio"], 
-        #                 "480P"
-        #             ])
-
-        #     if example_data:
-        #         gr.Examples(
-        #             examples=example_data,
-        #             inputs=[ref_img, video, resolution],
-        #             outputs=output_video,
-        #             fn=app.predict,
-        #             cache_examples=False,
-        #         )
-
-    demo.launch()
+        example_data = [
+            ['./examples/mov/1/1.jpeg', './examples/mov/1/1.mp4', 'wan2.2-animate-move', 'wan-pro'],
+            ['./examples/mov/2/2.jpeg', './examples/mov/2/2.mp4', 'wan2.2-animate-move', 'wan-pro'],
+            ['./examples/mix/1/1.jpeg', './examples/mix/1/1.mp4', 'wan2.2-animate-mix', 'wan-pro'],
+            ['./examples/mix/2/2.jpeg', './examples/mix/2/2.mp4', 'wan2.2-animate-mix', 'wan-pro']
+        ]
+
+        if example_data:
+            gr.Examples(
+                examples=example_data,
+                inputs=[ref_img, video, model_id, model],
+                outputs=output_video,
+                fn=app.predict,
+                cache_examples=False,
+            )
+
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860
+    )
 
 
 if __name__ == "__main__":

examples/mix/1/1.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a6d2e530e66e502f58d3983541c0194974b11662171079375e2649bfab3fe8
+size 593964

examples/mix/2/2.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6da60e5fcb0fda0bff151bfbdbb7085d5a86a78508743cce2a25709de86a19
+size 754294

examples/mov/1/1.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f3cfe3786a7f8a94844476448fb45e7e115216ddcdaad14b0b88223be597e7
+size 903201

examples/mov/2/2.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3ce91220c6018489bac2a546f58321f1afd40967e879e6a76b11b7745a5860
+size 524263