Alibaba Cloud Model Studio:Fine-tune a video generation model

First frame mode

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":[
        "<training_dataset_file_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
    }
}'

First and last frames mode

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":[
        "<training_dataset_file_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
    }
}'

Response

Key fields in output:

• job_id -- Use this to query training progress

• finetuned_output -- Fine-tuned model name for deployment and invocation

• status -- Initial: PENDING

{
    ...
    "output": {
        "job_id": "ft-202511111122-xxxx",
        "status": "PENDING",
        "finetuned_output": "xxxx-ft-202511111122-xxxx",
        ...
    }
}

First frame mode

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/deployments' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "<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"
}'

First and last frames mode

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/deployments' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "<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"
}'

Response

Key fields in output:

• deployed_model -- Model name for checking status and invocation

• status -- Initial: PENDING

{
    ...
    "output": {
        "deployed_model": "xxxx-ft-202511111122-xxxx",
        "status": "PENDING",
        ...
    }
}

First frame mode parameters

First and last frames mode parameters

First frame mode

The training set contains a first frame image, training video, and annotation file (data.jsonl).

• Sample: wan-i2v-training-dataset.zip

• Folder structure:

    wan-i2v-training-dataset.zip
    ├── data.jsonl        # Required. Max size: 20 MB.
    ├── image_1.jpeg      # Max resolution: 4096 x 4096. Formats: BMP, JPEG, PNG, WEBP.
    ├── video_1.mp4       # Max resolution: 4096 x 4096. Formats: MP4, MOV.
    ├── image_2.jpeg
    └── video_2.mp4

• Annotation file (data.jsonl): Each line is a JSON object representing one training sample.

    {
        "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"
    }

First and last frames mode

The training set contains a first frame image, a last frame image, a training video, and an annotation file (data.jsonl).

• Sample: wan-kf2v-training-dataset.zip

• Folder structure:

    wan-kf2v-training-dataset.zip
    ├── data.jsonl                # Required. Max size: 20 MB.
    ├── image/                    # First and last frame images.
    │   ├── image_1_first.jpg     # Max resolution: 4096 x 4096. Formats: BMP, JPEG, PNG, WEBP.
    │   └── image_1_last.png
    └── video/                    # Training videos.
        ├── video_1.mp4           # Max resolution: 4096 x 4096. Formats: MP4, MOV.
        └── video_2.mov

• Annotation file (data.jsonl):

    {
        "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"
    }

First frame mode

• Sample: wan-i2v-valid-dataset.zip

• Folder structure:

    wan-i2v-valid-dataset.zip
    ├── data.jsonl       # Required. Max size: 20 MB.
    ├── image_1.jpeg     # Max resolution: 4096 x 4096. Formats: BMP, JPEG, PNG, WEBP.
    └── image_2.jpeg

• Annotation file (data.jsonl):

    {
        "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"
    }

First and last frames mode

• Sample: wan-kf2v-valid-dataset.zip

• Folder structure:

    wan-kf2v-valid-dataset.zip
    ├── data.jsonl                 # Required. Max size: 20 MB.
    └── image/                     # First and last frame images.
        ├── image_1_first.jpg      # Max resolution: 4096 x 4096. Formats: BMP, JPEG, PNG, WEBP.
        └── image_1_last.jpg

• Annotation file (data.jsonl):

    {
        "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"
    }