> ## Documentation Index > Fetch the complete documentation index at: https://docs.aiid.edu.kg/llms.txt > Use this file to discover all available pages before exploring further. # Create video (Seedance) > This series supports OpenAI video generation formats (see the link [Video generation Sora compatible formats](/api-reference/en/video-generation-sora-compatible-format/create-video)). Used to create video generation tasks and query status and results via task ID. Core fields for task creation: - `model`: Required. Model name. - `prompt`: Required. Primary description for video generation. - `content`: Optional, the Volcano Ark content array, mixing text, image, video, and audio materials. - `function_mode`: Optional. Commonly used for advanced modes such as Omni-Reference. Compatible input parameters: The following fields are mainly used for compatibility with legacy clients and older protocols. For new integrations, please use the standard format in the “Request Example” on this page whenever possible: use the `content` array for text and reference materials, and use top-level `duration`, `ratio`, `resolution`, `fps`, and other fields for generation configuration. - `mode`：`t2v / i2v / i2v_first_last / reference_images / reference_material` - `image_url / image_urls / input_reference` - `end_image_url / last_image_url` - `video_urls / audio_urls` - `seconds / duration` - `aspect_ratio / ratio / size` - `quality / resolution` - `fps` - `generate_audio / watermark` Call details: - When using `mode=reference_material` or `function_mode=omni_reference`, it is recommended to pass text and reference materials via `content`. - `content` text items are written as `{ "type": "text", "text": "测试文字" }`. - `content` image, video, and audio material items use the `image_url`, `video_url`, and `audio_url` object formats respectively, for example `{ "type": "image_url", "image_url": { "url": "https://example.com/ref.png" }, "role": "reference_image", "name": "1" }`. - `role` can be used to identify the purpose of the material, and `name` can be referenced by name in prompts. - `ratio`, `duration`, `resolution`, and `fps` will affect the final generation configuration. Gemini Omni invocation: - `gemini-omni` can also be invoked through this Seedance task API. - `mode=t2v` is used for text-to-video, `mode=r2v` for generation with reference images/reference materials, and `mode=edit` for video editing. - Text can be placed in the `text` item of `prompt` or `content`; images can be placed in `image_url / image_urls / reference_images / input_reference / content`; videos can be placed in `video_urls / content`. - The duration field can use `duration` or `seconds`, and will be automatically mapped to the 4 / 6 / 8 / 10 second options. MiniMax / Hailuo Invocation: - `minimax-h3` can be invoked through this task API and supports text-to-video, image reference, and audio reference; text can be placed in the `prompt` or `content` text fields, and assets can be placed in fields such as `content`, `image_urls`, and `audio_urls`. - `hailuo-2.3` can be invoked through this task API. A first-frame image is required. It is recommended to pass the `image_url` item of `role=first_frame` in `content`. - `minimax-h3` commonly uses `duration=5~15` and `resolution=1440p`; `hailuo-2.3` commonly uses `duration=6` or `10` and `resolution=768p`. Key fields in query results: - `items[].status` - `items[].content.video_url` or `items[].video_url` - `items[].error` - `items[].progress` Error fields: `error.code`, `error.message`. ```json { "error": { "code": "invalid_request_error", "message": "requires at least one image in `images`" } } ``` ## OpenAPI ````yaml api-reference/en/openapi.json POST /api/v3/contents/generations/tasks openapi: 3.0.0 info: title: Overseas Expansion Camp API Reference Documentation version: 1.0.0 description: Public AI Gateway API Reference servers: - url: https://api.aiid.edu.kg security: - BearerAuth: [] tags: - name: OpenAI format (Chat) - name: OpenAI Format (Responses) - name: Gemini Format for Image Generation - name: Image generationOpenAI DALL-E format - name: List models - name: Video generationHappyHorse and Wan - name: Video generation Kling format - name: Video generation Omni and Veo formats - name: Video generation Seedance - name: Video generation Sora compatible formats - name: Video generation Vidu - name: Music generation task format paths: /api/v3/contents/generations/tasks: post: tags: - Video generation Seedance summary: Create video (Seedance) description: >- This series supports OpenAI video generation formats (see the link [Video generation Sora compatible formats](/api-reference/en/video-generation-sora-compatible-format/create-video)). Used to create video generation tasks and query status and results via task ID. Core fields for task creation: - `model`: Required. Model name. - `prompt`: Required. Primary description for video generation. - `content`: Optional, the Volcano Ark content array, mixing text, image, video, and audio materials. - `function_mode`: Optional. Commonly used for advanced modes such as Omni-Reference. Compatible input parameters: The following fields are mainly used for compatibility with legacy clients and older protocols. For new integrations, please use the standard format in the “Request Example” on this page whenever possible: use the `content` array for text and reference materials, and use top-level `duration`, `ratio`, `resolution`, `fps`, and other fields for generation configuration. - `mode`：`t2v / i2v / i2v_first_last / reference_images / reference_material` - `image_url / image_urls / input_reference` - `end_image_url / last_image_url` - `video_urls / audio_urls` - `seconds / duration` - `aspect_ratio / ratio / size` - `quality / resolution` - `fps` - `generate_audio / watermark` Call details: - When using `mode=reference_material` or `function_mode=omni_reference`, it is recommended to pass text and reference materials via `content`. - `content` text items are written as `{ "type": "text", "text": "测试文字" }`. - `content` image, video, and audio material items use the `image_url`, `video_url`, and `audio_url` object formats respectively, for example `{ "type": "image_url", "image_url": { "url": "https://example.com/ref.png" }, "role": "reference_image", "name": "1" }`. - `role` can be used to identify the purpose of the material, and `name` can be referenced by name in prompts. - `ratio`, `duration`, `resolution`, and `fps` will affect the final generation configuration. Gemini Omni invocation: - `gemini-omni` can also be invoked through this Seedance task API. - `mode=t2v` is used for text-to-video, `mode=r2v` for generation with reference images/reference materials, and `mode=edit` for video editing. - Text can be placed in the `text` item of `prompt` or `content`; images can be placed in `image_url / image_urls / reference_images / input_reference / content`; videos can be placed in `video_urls / content`. - The duration field can use `duration` or `seconds`, and will be automatically mapped to the 4 / 6 / 8 / 10 second options. MiniMax / Hailuo Invocation: - `minimax-h3` can be invoked through this task API and supports text-to-video, image reference, and audio reference; text can be placed in the `prompt` or `content` text fields, and assets can be placed in fields such as `content`, `image_urls`, and `audio_urls`. - `hailuo-2.3` can be invoked through this task API. A first-frame image is required. It is recommended to pass the `image_url` item of `role=first_frame` in `content`. - `minimax-h3` commonly uses `duration=5~15` and `resolution=1440p`; `hailuo-2.3` commonly uses `duration=6` or `10` and `resolution=768p`. Key fields in query results: - `items[].status` - `items[].content.video_url` or `items[].video_url` - `items[].error` - `items[].progress` Error fields: `error.code`, `error.message`. ```json { "error": { "code": "invalid_request_error", "message": "requires at least one image in `images`" } } ``` operationId: create__seedance__task requestBody: required: true content: application/json: schema: type: object required: - model - prompt properties: model: type: string example: doubao-seedance-2-0-260128 enum: - doubao-seedance-1-0-lite-i2v-250428 - doubao-seedance-1-0-lite-t2v-250428 - doubao-seedance-1-0-pro-250528 - doubao-seedance-1-0-pro-fast-251015 - doubao-seedance-1-5-pro-251215 - doubao-seedance-2-0-260128 - doubao-seedance-2-0-fast-260128 - minimax-h3 - hailuo-2.3 - gemini-omni description: >- Required. Model name. You can pass the Seedance external model, `gemini-omni`, `minimax-h3`, or `hailuo-2.3`. prompt: type: string example: 参考素材生成一段剧情短视频 description: >- Required. The primary description for video generation; cannot be empty. content: type: array description: >- Optional. The Volcano Ark content array, which interleaves text and media items in order. Text items use `{ "type": "text", "text": "..." }`; image, video, and audio items use `image_url`, `video_url`, and `audio_url` objects respectively, with `url` placed inside them. These can be used together with `role` (such as `reference_image`, `reference_video`, and `reference_audio`) and `name` for text references. items: type: object required: - type properties: type: type: string enum: - text - image_url - video_url - audio_url description: Content item type. text: type: string description: Text content, used only when type=text. image_url: oneOf: - type: string - type: object properties: url: type: string description: >- Image URL. Recommended object format: `{"url":"https://..."}`. video_url: oneOf: - type: string - type: object properties: url: type: string description: >- Video URL. Recommended object syntax: `{"url":"https://..."}`. audio_url: oneOf: - type: string - type: object properties: url: type: string description: >- Audio URL. Recommended object format: `{"url":"https://..."}`. role: type: string description: >- Asset usage identifier. Common values include reference_image, reference_video, and reference_audio. name: type: string description: >- Asset name, can be referenced in text prompts or used to distinguish between multiple assets. function_mode: type: string description: >- Optional. Advanced feature mode, such as `omni_reference` for all-in-one reference. mode: type: string description: >- Optional. Compatibility mode fields, such as `t2v`, `i2v`, `i2v_first_last`, `reference_images`, and `reference_material`; `gemini-omni` supports `t2v`, `r2v`, and `edit`. image_url: type: string description: Optional. URL of a single reference image. image_urls: type: array items: type: string description: Optional. A list of URLs for multiple reference images. input_reference: type: string description: Optional. Compatible with reference input fields. end_image_url: type: string description: Optional. The URL of the last-frame reference image. last_image_url: type: string description: Optional. URL alias for the last frame reference image. video_urls: type: array items: type: string description: Optional. List of reference video URLs. audio_urls: type: array items: type: string description: Optional. List of reference audio URLs. seconds: oneOf: - type: number - type: string description: >- Optional. Video duration in seconds; compatible with `duration`. duration: oneOf: - type: number - type: string description: >- Optional. Video duration in seconds; compatible with `seconds`. aspect_ratio: type: string description: Optional. Aspect ratio, such as `16:9`. ratio: type: string description: Optional. Aspect ratio aliases, such as `16:9`. size: type: string description: Optional. Field for resolution or dimension compatibility. quality: type: string description: Optional. Generation quality configuration. resolution: type: string description: Optional. The output resolution. fps: type: number description: Optional. Frame rate. generate_audio: type: boolean description: Optional. Whether to generate audio. watermark: type: boolean description: Optional. Whether to add a watermark. examples: seedance_tasks_reference_material: summary: Seedance content task value: model: doubao-seedance-1-0-lite-i2v-250428 mode: reference_material prompt: 测试文字 content: - type: text text: 测试文字 - type: image_url image_url: url: >- https://imageproxy.zhongzhuan.chat/api/proxy/image/9979f1a754b3571d5e8bdcc397eedf53.png role: reference_image name: '1' - type: video_url video_url: url: >- https://imageproxy.zhongzhuan.chat/api/proxy/video/1979f1a754b3571d5e8bdcc397eedf53.mp4 role: reference_video name: '2' - type: audio_url audio_url: url: >- https://imageproxy.zhongzhuan.chat/api/proxy/video/3979f1a754b3571d5e8bdcc397eedf53.mp3 role: reference_audio name: '3' duration: 5 size: 1280x720 minimax_h3_tasks_content: summary: MiniMax H3 content task value: model: minimax-h3 prompt: A cinematic product video with smooth camera motion content: - type: text text: >- Use the product image as reference and match the rhythm of the audio. - type: image_url image_url: url: https://example.com/product.jpg role: reference_image name: product - type: audio_url audio_url: url: https://example.com/music.mp3 role: reference_audio name: music duration: 8 resolution: 1440p ratio: '16:9' generate_audio: true hailuo_2_3_tasks_first_frame: summary: Hailuo 2.3 First-frame image-to-video value: model: hailuo-2.3 prompt: >- The camera slowly pushes in, natural motion and cinematic lighting. content: - type: text text: >- The camera slowly pushes in, natural motion and cinematic lighting. - type: image_url image_url: url: https://example.com/first-frame.jpg role: first_frame name: first duration: 10 resolution: 768p ratio: '16:9' gemini_omni_seedance_t2v: summary: Gemini Omni t2v value: model: gemini-omni mode: t2v prompt: A cinematic product video with smooth camera motion duration: 8 size: 1280x720 gemini_omni_seedance_r2v: summary: Gemini Omni r2v value: model: gemini-omni mode: r2v content: - type: text text: Keep the product consistent and create a short ad video - type: image_url image_url: url: https://example.com/product.jpg duration: 8 size: 1280x720 gemini_omni_seedance_edit: summary: Gemini Omni edit value: model: gemini-omni mode: edit content: - type: text text: Change the outfit color while keeping the motion natural - type: video_url video_url: url: https://example.com/input.mp4 - type: image_url image_url: url: https://example.com/style.jpg duration: 8 size: 1280x720 responses: '200': description: Task created successfully content: application/json: schema: type: object required: - id properties: id: type: string example: task_xxx description: Task ID. status: type: string description: Task status. enum: - queued - running - succeeded - failed created_at: type: string description: Creation time (Unix seconds). items: type: string items: type: object properties: id: type: string description: Task ID. status: type: string description: >- Task status, commonly `queued`, `running`, `succeeded`, and `failed`. content: type: object properties: video_url: type: string description: Video result URL. video_url: type: string description: Video result URL. error: type: string description: Error message returned when the request fails. progress: type: string description: Task progress. security: - BearerAuth: [] components: securitySchemes: BearerAuth: type: http scheme: bearer description: |- Use Bearer Token authentication. Format: `Authorization: Bearer sk-xxxxxx` ````