大模型服务平台百炼：微调视频生成模型

图生视频-基于首帧

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/fine-tunes' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model":"wan2.6-i2v",
    "training_file_ids":[
        "<替换为训练数据集的文件id>"
    ],
    "training_type":"efficient_sft",
    "hyper_parameters":{
        "n_epochs":400,
        "batch_size":2,
        "learning_rate":2e-5,
        "split":0.9,
        "eval_epochs": 50,
        "max_pixels": 36864
    }
}'

图生视频-基于首尾帧

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/fine-tunes' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model":"wan2.2-kf2v-flash",
    "training_file_ids":[
        "<替换为训练数据集的文件id>"
    ],
    "training_type":"efficient_sft",
    "hyper_parameters":{
        "n_epochs":400,
        "batch_size":4,
        "learning_rate":2e-5,
        "split":0.9,
        "eval_epochs": 50,
        "max_pixels": 262144
    }
}'

图生视频-基于首帧

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/deployments' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "<替换为模型名称model_name>",
    "aigc_config": {
        "use_input_prompt": false,
        "prompt": "Provide a video description based on the image content. The description must include the phrase “Then the s86b5p money rain effect begins, countless huge-sized US dollar bills (beige background/dark green patterns) pour down like a torrential rain, densely hitting and surrounding her. The bills continue to fall, she/he stretches her/his arms upward, neck slightly tilted back, expression surprised, completely immersed in this wild money rain.“\nOutput Template:\nThe video begins with a shot of [subject description]. [Environment description]. Then the s86b5p money rain effect begins, countless huge-sized US dollar bills (beige background/dark green patterns) pour down like a torrential rain, densely hitting and surrounding her. The bills continue to fall, she/he stretches her/his arms upward, neck slightly tilted back, expression surprised, completely immersed in this wild money rain.\nExample:\nThe video begins showing a young woman standing in front of a brick wall covered with ivy. She has long, smooth reddish-brown hair, wearing a white sleeveless dress, a shiny silver necklace, and a smile on her face. The brick wall in the background is covered with green vines, appearing rustic and natural. Then the s86b5p money rain effect begins, countless huge-sized US dollar bills (beige background/dark green patterns) pour down like a torrential rain, densely hitting and surrounding her. The bills continue to fall, she stretches her arms upward, neck slightly tilted back, expression surprised, completely immersed in this wild money rain.",
        "lora_prompt_default": "Then the s86b5p money rain effect begins, countless huge-sized US dollar bills (beige background/dark green patterns) pour down like a torrential rain, densely hitting and surrounding her. The bills continue to fall, she/he stretches her/his arms upward, neck slightly tilted back, expression surprised, completely immersed in this wild money rain."
    },
    "capacity": 1,
    "plan": "lora"
}'

图生视频-基于首尾帧

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/deployments' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "<替换为模型名称model_name>",
    "aigc_config": {
        "use_input_prompt": false,
        "prompt": "Provide a video description based on the image content. The description must include the phrase “Then she/he begins the s86b5p transformation.“\nOutput Template:\nThe video begins with a shot of [subject description]. [Environment description]. Then she/he begins the s86b5p transformation.\nExample:\nThe video begins with a young woman in an outdoor setting. She has short, curly dark brown hair and a friendly smile. She is wearing a black Polo shirt with colorful floral embroidery. The background features green vegetation and distant mountains. Then she begins the s86b5p transformation.",
        "lora_prompt_default": "Then she/he begins the s86b5p transformation."
    },
    "capacity": 1,
    "plan": "lora"
}'

图生视频-基于首帧

训练集包括首帧图像、训练视频和标注文件（data.jsonl）。

• 训练集样例：wan-i2v-training-dataset.zip。

• zip包目录结构：

  wan-i2v-training-dataset.zip
  ├── data.jsonl        # 必须固定命名为data.jsonl，最大支持 20MB
  ├── image_1.jpeg      # 图像最大分辨率为4096*4096，支持BMP、JPEG、PNG、WEBP格式
  ├── video_1.mp4       # 视频最大分辨率为4096*4096，支持MP4、MOV格式
  ├── image_2.jpeg
  └── video_2.mp4

• 标注文件（data.jsonl）：每一行代表一条训练数据，必须为JSON 对象。一行训练数据的结构如下：

  {
      "prompt": "The video begins showing a young woman standing in front of a brick wall covered with ivy. She has long, smooth reddish-brown hair, wearing a white sleeveless dress, a shiny silver necklace, and a smile on her face. The brick wall in the background is covered with green vines, appearing rustic and natural. Then the s86b5p money rain effect begins, countless huge-sized US dollar bills (beige background/dark green patterns) pour down like a torrential rain, densely hitting and surrounding her. The bills continue to fall, she stretches her arms upward, neck slightly tilted back, expression surprised, completely immersed in this wild money rain.",
      "first_frame_path": "image_1.jpg",
      "video_path": "video_1.mp4"        
  }

图生视频-基于首尾帧

训练集包括首帧图像、尾帧图像、训练视频和标注文件（data.jsonl）。

• 训练集样例：wan-kf2v-training-dataset.zip。

• zip包目录结构：

  wan-kf2v-training-dataset.zip
  ├── data.jsonl                # 必须固定命名为data.jsonl，最大支持 20MB
  ├── image/                    # 存放首帧和尾帧图像
  │   ├── image_1_first.jpg     # 图像最大分辨率为4096*4096，支持BMP、JPEG、PNG、WEBP格式
  │   └── image_1_last.png
  └── video/                    # 存放作为“训练目标”的视频文件
      ├── video_1.mp4           # 视频最大分辨率为4096*4096，支持MP4、MOV格式
      └── video_2.mov

• 标注文件（data.jsonl）：每一行代表一条训练数据，必须为JSON 对象。一行训练数据的结构如下：

  {
      "prompt": "The video begins by showing a young woman in an outdoor setting. She has short, curly dark brown hair, a smile on her face, and looks very friendly. She is wearing a black polo shirt with colorful floral embroidery, with a background of green vegetation and distant mountains. Then she begins the s86b5p transformation.",
      "first_frame_path": "image/image_1_first.jpg",
      "last_frame_path": "image/image_1_last.jpg", 
      "video_path": "video/video_1.mp4"  
  }

图生视频-基于首帧

验证集包括首帧图像和标注文件（data.jsonl），无需提供视频。训练任务会在每个评估节点，自动调用模型服务，使用验证集的图像和 Prompt 生成预览视频。

• 验证集样例：wan-i2v-valid-dataset.zip。

• zip包目录结构：

  wan-i2v-valid-dataset.zip
  ├── data.jsonl       # 必须固定命名为data.jsonl，最大支持 20MB
  ├── image_1.jpeg     # 图像最大分辨率为4096*4096，支持BMP、JPEG、PNG、WEBP格式
  └── image_2.jpeg

• 标注文件（data.jsonl）：每一行代表一条验证数据，必须为JSON 对象。一行验证数据的结构如下：

  {
      "prompt": "The video begins showing a scene of a young man standing in front of a cityscape. He is wearing a black and white checkered jacket over a black hoodie, with a smile on his face and a confident expression. The background is a city skyline at sunset, with a famous domed building and layered roofs visible in the distance, the sky filled with clouds showing warm orange-yellow hues. Then the s86b5p money rain effect begins, countless huge-sized US dollar bills (beige background/dark green patterns) pour down like a torrential rain, densely hitting and surrounding him. The bills continue to fall while the camera slowly zooms in, he stretches his arms upward, neck slightly tilted back, expression surprised, completely immersed in this wild money rain.",
      "first_frame_path": "image_1.jpg"
  }

图生视频-基于首尾帧

验证集包括首帧图像、尾帧图像和标注文件（data.jsonl），无需提供视频。训练任务会在每个评估节点，自动调用模型服务，使用验证集的图像和 Prompt 生成预览视频。

• 验证集样例：wan-kf2v-valid-dataset.zip。

• zip包目录结构：

  wan-kf2v-valid-dataset.zip
  ├── data.jsonl                 # 必须固定命名为data.jsonl，最大支持 20MB
  └── image/                     # 存放首帧和尾帧图像
      ├── image_1_first.jpg      # 图像最大分辨率为4096*4096，支持BMP、JPEG、PNG、WEBP格式
      └── image_1_last.jpg

• 标注文件（data.jsonl）：每一行代表一条验证数据，必须为JSON 对象。一行验证数据的结构如下：

  {
      "prompt": "The video begins showing a scene of a young man standing in front of a cityscape. He is wearing a black and white checkered jacket over a black hoodie, with a smile on his face and a confident expression. The background is a city skyline at sunset, with a famous domed building and layered roofs visible in the distance, the sky filled with clouds showing warm orange-yellow hues. Then the s86b5p money rain effect begins, countless huge-sized US dollar bills (beige background/dark green patterns) pour down like a torrential rain, densely hitting and surrounding him. The bills continue to fall while the camera slowly zooms in, he stretches his arms upward, neck slightly tilted back, expression surprised, completely immersed in this wild money rain.",
      "first_frame_path": "image/image_1_first.jpg",
      "last_frame_path": "image/image_1_last.jpg",
  }