Alibaba Cloud Model Studio:Fine-tuning model pembuatan video

Image-to-video (berbasis frame pertama)

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/fine-tunes' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "wan2.7-i2v",
    "training_file_ids": [
        "<your-training-dataset-file-id>"
    ],
    "training_type": "efficient_sft",
    "hyper_parameters": {
        "n_epochs": 400,
        "batch_size": 1,
        "learning_rate": 2e-5,
        "split": 0.9,
        "max_split_val_dataset_sample": 5,
        "eval_epochs": 50,
        "max_pixels": 102400,
        "save_total_limit": 10,
        "lora_rank": 32,
        "lora_alpha": 32
    }
}'

Image-to-video (berbasis frame pertama dan terakhir)

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": [
        "<your-training-dataset-file-id>"
    ],
    "training_type": "efficient_sft",
    "hyper_parameters": {
        "n_epochs": 400,
        "batch_size": 4,
        "learning_rate": 2e-5,
        "split": 0.9,
        "max_split_val_dataset_sample": 5,
        "eval_epochs": 50,
        "max_pixels": 262144,
        "save_total_limit": 10,
        "lora_rank": 32,
        "lora_alpha": 32
    }
}'

Image-to-video (berbasis frame pertama)

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/deployments' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "<your-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 them. The bills continue to fall, while the camera slowly zooms in, they stretch their 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 them. The bills continue to fall, while the camera slowly zooms in, they stretch their 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, while the camera slowly zooms in, 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 the main character. The bills continue to fall, while the camera slowly zooms in, the main character stretches their arms upward, neck slightly tilted back, with a surprised expression, completely immersed in this wild money rain."
    },
    "capacity": 1,
    "plan": "lora"
}'

Image-to-video (berbasis frame pertama dan terakhir)

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/deployments' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "<your-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 they begin the s86b5p transformation.”\nOutput Template:\nThe video begins with a shot of [subject description]. [Environment description]. Then they begin 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 they begin the s86b5p transformation."
    },
    "capacity": 1,
    "plan": "lora"
}'

Image-to-video (berbasis frame pertama)

Set pelatihan mencakup gambar frame pertama, video pelatihan, dan file anotasi (data.jsonl).

• Set pelatihan contoh: wan-i2v-training-dataset.zip.

• Struktur direktori ZIP:

  wan-i2v-training-dataset.zip
  ├── data.jsonl        # Harus bernama data.jsonl. Ukuran maks: 20 MB.
  ├── image_1.jpeg      # Resolusi maks: 4096×4096. Format: BMP, JPEG, PNG, WEBP.
  ├── video_1.mp4       # Resolusi maks: 4096×4096. Format: MP4, MOV.
  ├── image_2.jpeg
  └── video_2.mp4

• File anotasi (data.jsonl): Setiap baris adalah satu sampel pelatihan. Harus berupa objek JSON. Struktur:

  {
      "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"        
  }

Image-to-video (berbasis frame pertama dan terakhir)

Set pelatihan mencakup gambar frame pertama, gambar frame terakhir, video pelatihan, dan file anotasi (data.jsonl).

• Set pelatihan contoh: wan-kf2v-training-dataset.zip.

• Struktur direktori ZIP:

  wan-kf2v-training-dataset.zip
  ├── data.jsonl                # Harus bernama data.jsonl. Ukuran maks: 20 MB.
  ├── image/                    # Gambar frame pertama dan terakhir.
  │   ├── image_1_first.jpg     # Resolusi maks: 4096×4096. Format: BMP, JPEG, PNG, WEBP.
  │   └── image_1_last.png
  └── video/                    # Video pelatihan.
      ├── video_1.mp4           # Resolusi maks: 4096×4096. Format: MP4, MOV.
      └── video_2.mov

• File anotasi (data.jsonl): Setiap baris adalah satu sampel pelatihan. Harus berupa objek JSON. Struktur:

  {
      "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"  
  }

Image-to-video (berbasis frame pertama)

Set validasi mencakup gambar frame pertama dan file anotasi (data.jsonl). Video tidak diperlukan. Di setiap titik evaluasi, pekerjaan pelatihan secara otomatis memanggil layanan model untuk menghasilkan video pratinjau menggunakan gambar dan prompt validasi.

• Set validasi contoh: wan-i2v-valid-dataset.zip.

• Struktur direktori ZIP:

  wan-i2v-valid-dataset.zip
  ├── data.jsonl       # Harus bernama data.jsonl. Ukuran maks: 20 MB.
  ├── image_1.jpeg     # Resolusi maks: 4096×4096. Format: BMP, JPEG, PNG, WEBP.
  └── image_2.jpeg

• File anotasi (data.jsonl): Setiap baris adalah satu sampel validasi. Harus berupa objek JSON. Struktur:

  {
      "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"
  }

Image-to-video (berbasis frame pertama dan terakhir)

Set validasi mencakup gambar frame pertama, gambar frame terakhir, dan file anotasi (data.jsonl). Video tidak diperlukan. Di setiap titik evaluasi, pekerjaan pelatihan secara otomatis memanggil layanan model untuk menghasilkan video pratinjau menggunakan gambar dan prompt validasi.

• Set validasi contoh: wan-kf2v-valid-dataset.zip.

• Struktur direktori ZIP:

  wan-kf2v-valid-dataset.zip
  ├── data.jsonl                 # Harus bernama data.jsonl. Ukuran maks: 20 MB.
  └── image/                     # Gambar frame pertama dan terakhir.
      ├── image_1_first.jpg      # Resolusi maks: 4096×4096. Format: BMP, JPEG, PNG, WEBP.
      └── image_1_last.jpg

• File anotasi (data.jsonl): Setiap baris adalah satu sampel validasi. Harus berupa objek JSON. Struktur:

  {
      "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",
  }