> ## 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. # 创建视频 > OpenAI Sora 兼容格式的视频生成接口。支持文生视频与图/视频参考生成模式。 - `POST /v1/videos`：创建视频任务 - `GET /v1/videos/{video_id}`：查询任务状态 - `GET /v1/videos/{video_id}/content`：获取视频二进制内容 当前对外不提供： - `GET /v1/videos` - `POST /v1/videos/{video_id}/remix` 标准鉴权头： - `Content-Type: application/json` 1. `POST /v1/videos` 创建任务，获取 `id` 2. 轮询 `GET /v1/videos/{id}` 直到 `completed` 或 `failed` 3. 完成后优先使用返回中的 `video_url` 4. 如需统一下载，调用 `GET /v1/videos/{id}/content` 核心参数： - `model: string`：必填，对外模型名 - `prompt: string`：推荐，视频生成描述 - `seconds: number|string`：可选，目标时长 - `duration: number|string`：可选，时长别名 - `size: string`：可选，输出尺寸 - `mode: string`：可选，常见值 `t2v` `i2v` `i2v_first_last` `reference_material` 常用兼容参数： - `aspect_ratio` - `ratio` - `quality` - `resolution` - `fps` - `image` - `image_url` - `image_urls` - `images` - `reference_images` - `input_reference` - `end_image_url` - `last_image_url` - `video_urls` - `audio_urls` - `function_mode` - `content` - `callback_url` - `external_task_id` Kling 常用扩展参数： - `model_name` - `negative_prompt` - `cfg_scale` - `sound` - `camera_control` - `image_list` - `video_id` - `task_id` - `watermark_info` ### 4.1 Veo 系列 说明：`stable`、`official` 等表示不同分组，不是对外 `model` 后缀；调用时请保持 `model` 为基础模型名，由账户或令牌分组决定实际走哪个分组。 #### Veo 3.x 主模型 - `veo3` - `veo3-fast` - `veo3-fast-frames` - `veo3-frames` - `veo3-pro` - `veo3-pro-frames` - `veo3.1` - `veo3.1-fast` - `veo3.1-pro` - `veo3.1-components` - `veo3.1-4k` - `veo3.1-pro-4k` 建议： - 纯文生视频优先使用 `veo3*` / `veo3.1*` 主模型 - 图生或参考生视频场景，建议显式传 `mode + image_url/reference_images` ### 4.2 Sora 系列 基础模型： - `sora-2` - `sora-2-pro` 建议： - `sora-2*` 适合通用调用 - 如需使用 `stable` / `official` 等分组，请保持 `model` 为基础模型名，不要在模型名后追加后缀。 请求示例： ```json { "size": "1280x720", "images": [ "https://example.png" ], "model": "sora-2", "prompt": "this is an example", "duration": 12, "fps": "24", "seed": "20231024", "mode": "i2v" } ``` ### 4.3 HappyHorse 系列 对外模型： - `happyhorse-1.0` 建议： - `happyhorse-1.0` 通过 `mode` 区分 `t2v`、`i2v`、`r2v`、`video_edit`。 - Sora 兼容格式中参考图建议使用 `content` 数组传递媒体项。 - 文本项使用 `type=text`，媒体项使用 `type=image_url` 并可配合 `role`、`name` 标识素材用途。 请求示例： ```json { "size": "720x1280", "model": "happyhorse-1.0", "mode": "r2v", "prompt": "this is an example", "duration": 15, "content": [ { "type": "text", "text": "this is an example" }, { "type": "image_url", "image_url": { "url": "https://example.png" }, "role": "reference_image", "name": "image1" } ], "parameters": { "resolution": "720P", "ratio": "9:16", "duration": 15, "seed": 1 } } ``` ### 4.4 Seedance 系列 对外模型： - `doubao-seedance-1-0-lite-t2v-250428` - `doubao-seedance-1-0-lite-i2v-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` 建议： - 文生视频优先 `*-t2v-*` 或 `pro / fast` - 图生视频优先 `*-i2v-*` - 复杂参考素材场景优先使用 `content` 请求示例： ```json { "size": "1280x720", "model": "doubao-seedance-2-0-fast-260128", "prompt": "this is an example", "duration": 15, "fps": "24", "seed": "20231024", "mode": "reference_material", "content": [ { "type": "text", "text": "this is an example" }, { "type": "image_url", "image_url": { "url": "https://example.png" }, "role": "reference_image", "name": "image1" }, { "type": "audio_url", "audio_url": { "url": "https://example.mp3" }, "role": "reference_audio", "name": "audio1" } ] } ``` ### 4.5 Grok 视频系列 对外模型： - `grok-imagine-1.0-video` - `grok-imagine-video-1.5-preview` - `grok-video-3` 常用参数： - `prompt` - `ratio` / `aspect_ratio` - `resolution` / `size` - `seconds` / `duration` - `image` / `image_url` / `input_reference` - `reference_images` 示例： ```json { "model": "grok-imagine-1.0-video", "prompt": "雨夜霓虹街道上的电影感推镜，光影丰富，运动自然", "reference_images": [ "https://example.com/ref-1.jpg" ], "seconds": 10, "aspect_ratio": "16:9", "resolution": "720P" } ``` ### 4.6 Kling 视频主模型 对外主模型： - `kling-video` 必填： - `model` - `model_name` 支持的 `model_name`： - `kling-v1` - `kling-v1-5` - `kling-v1-6` - `kling-v2-master` - `kling-v2-1` - `kling-v2-1-master` - `kling-v2-5-turbo` - `kling-v2-6` - `kling-v3` 常见 `mode`： - `t2v` - `i2v` - `multi_i2v` - `extend` 最小入参： - 文生视频：`model + model_name + prompt + mode=t2v` - 图生视频：`model + model_name + prompt + mode=i2v + image` - 多图参考：`model + model_name + prompt + mode=multi_i2v + image_list` - 视频延长：`model + model_name + mode=extend + video_id` 示例： ```json { "model": "kling-video", "model_name": "kling-v2-6", "mode": "t2v", "prompt": "海边日落镜头，电影感，风吹长发", "duration": 5, "aspect_ratio": "16:9" } ``` ### 4.7 MiniMax / Hailuo 视频系列 对外模型： - `minimax-h3` - `hailuo-2.3` 建议： - `minimax-h3` 支持文生视频、图片参考和音频参考，推荐通过 `content` 混排文本与素材；也可使用 `image_urls`、`audio_urls` 等兼容字段。 - `hailuo-2.3` 需要首帧图片，推荐在 `content` 中传 `role=first_frame` 的 `image_url` 项，或使用 `image_urls` 传首帧图片。 - `minimax-h3` 常用 `duration=5~15`、`resolution=1440p`；`hailuo-2.3` 常用 `duration=6` 或 `10`、`resolution=768p`。 `minimax-h3` 示例： ```json { "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", "aspect_ratio": "16:9", "generate_audio": true } ``` `hailuo-2.3` 示例： ```json { "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", "aspect_ratio": "16:9" } ``` - `mode=t2v` - 最小入参：`model + prompt` - `mode=i2v` - 最小入参：`model + prompt + image_url` - `mode=i2v_first_last` - 最小入参：`model + prompt + image_url + end_image_url` - `mode=reference_images` - 最小入参：`model + prompt + reference_images` - `mode=reference_material` - 最小入参：`model + prompt + (image_urls/video_urls/audio_urls 至少一种)` ### Gemini Omni 调用说明 - `gemini-omni` 是 new-api 对外公开的视频模型名，可直接走 `POST /v1/videos`。 - `mode=t2v`：文生视频，最小入参为 `model + prompt`。 - `mode=r2v`：参考图/参考素材生成，图片可放在 `image`、`image_url`、`images`、`image_urls`、`reference_images`、`input_reference` 或 `content` 中。 - `mode=edit`：视频编辑，视频可放在 `video`、`video_url`、`videos` 或 `content` 中，也可同时传参考图。 - 时长字段可用 `seconds` 或 `duration`，会自动匹配到 4 / 6 / 8 / 10 秒档。 ## OpenAPI ````yaml api-reference/cn/openapi.json POST /v1/videos openapi: 3.0.0 info: title: 出海营 API 参考文档 version: 1.0.0 description: Public AI Gateway API Reference servers: - url: https://api.aiid.edu.kg security: - BearerAuth: [] tags: - name: OpenAI格式(Chat) - name: OpenAI格式(Responses) - name: 图片生成Gemini格式 - name: 图片生成OpenAI DALL-E格式 - name: 获取模型列表 - name: 视频生成HappyHorse与Wan - name: 视频生成Kling格式 - name: 视频生成Omni与Veo格式 - name: 视频生成Seedance格式 - name: 视频生成Sora兼容格式 - name: 视频生成Vidu格式 - name: 音乐生成任务格式 paths: /v1/videos: post: tags: - 视频生成Sora兼容格式 summary: 创建视频 description: >- OpenAI Sora 兼容格式的视频生成接口。支持文生视频与图/视频参考生成模式。 - `POST /v1/videos`：创建视频任务 - `GET /v1/videos/{video_id}`：查询任务状态 - `GET /v1/videos/{video_id}/content`：获取视频二进制内容 当前对外不提供： - `GET /v1/videos` - `POST /v1/videos/{video_id}/remix` 标准鉴权头： - `Content-Type: application/json` 1. `POST /v1/videos` 创建任务，获取 `id` 2. 轮询 `GET /v1/videos/{id}` 直到 `completed` 或 `failed` 3. 完成后优先使用返回中的 `video_url` 4. 如需统一下载，调用 `GET /v1/videos/{id}/content` 核心参数： - `model: string`：必填，对外模型名 - `prompt: string`：推荐，视频生成描述 - `seconds: number|string`：可选，目标时长 - `duration: number|string`：可选，时长别名 - `size: string`：可选，输出尺寸 - `mode: string`：可选，常见值 `t2v` `i2v` `i2v_first_last` `reference_material` 常用兼容参数： - `aspect_ratio` - `ratio` - `quality` - `resolution` - `fps` - `image` - `image_url` - `image_urls` - `images` - `reference_images` - `input_reference` - `end_image_url` - `last_image_url` - `video_urls` - `audio_urls` - `function_mode` - `content` - `callback_url` - `external_task_id` Kling 常用扩展参数： - `model_name` - `negative_prompt` - `cfg_scale` - `sound` - `camera_control` - `image_list` - `video_id` - `task_id` - `watermark_info` ### 4.1 Veo 系列 说明：`stable`、`official` 等表示不同分组，不是对外 `model` 后缀；调用时请保持 `model` 为基础模型名，由账户或令牌分组决定实际走哪个分组。 #### Veo 3.x 主模型 - `veo3` - `veo3-fast` - `veo3-fast-frames` - `veo3-frames` - `veo3-pro` - `veo3-pro-frames` - `veo3.1` - `veo3.1-fast` - `veo3.1-pro` - `veo3.1-components` - `veo3.1-4k` - `veo3.1-pro-4k` 建议： - 纯文生视频优先使用 `veo3*` / `veo3.1*` 主模型 - 图生或参考生视频场景，建议显式传 `mode + image_url/reference_images` ### 4.2 Sora 系列 基础模型： - `sora-2` - `sora-2-pro` 建议： - `sora-2*` 适合通用调用 - 如需使用 `stable` / `official` 等分组，请保持 `model` 为基础模型名，不要在模型名后追加后缀。 请求示例： ```json { "size": "1280x720", "images": [ "https://example.png" ], "model": "sora-2", "prompt": "this is an example", "duration": 12, "fps": "24", "seed": "20231024", "mode": "i2v" } ``` ### 4.3 HappyHorse 系列 对外模型： - `happyhorse-1.0` 建议： - `happyhorse-1.0` 通过 `mode` 区分 `t2v`、`i2v`、`r2v`、`video_edit`。 - Sora 兼容格式中参考图建议使用 `content` 数组传递媒体项。 - 文本项使用 `type=text`，媒体项使用 `type=image_url` 并可配合 `role`、`name` 标识素材用途。 请求示例： ```json { "size": "720x1280", "model": "happyhorse-1.0", "mode": "r2v", "prompt": "this is an example", "duration": 15, "content": [ { "type": "text", "text": "this is an example" }, { "type": "image_url", "image_url": { "url": "https://example.png" }, "role": "reference_image", "name": "image1" } ], "parameters": { "resolution": "720P", "ratio": "9:16", "duration": 15, "seed": 1 } } ``` ### 4.4 Seedance 系列 对外模型： - `doubao-seedance-1-0-lite-t2v-250428` - `doubao-seedance-1-0-lite-i2v-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` 建议： - 文生视频优先 `*-t2v-*` 或 `pro / fast` - 图生视频优先 `*-i2v-*` - 复杂参考素材场景优先使用 `content` 请求示例： ```json { "size": "1280x720", "model": "doubao-seedance-2-0-fast-260128", "prompt": "this is an example", "duration": 15, "fps": "24", "seed": "20231024", "mode": "reference_material", "content": [ { "type": "text", "text": "this is an example" }, { "type": "image_url", "image_url": { "url": "https://example.png" }, "role": "reference_image", "name": "image1" }, { "type": "audio_url", "audio_url": { "url": "https://example.mp3" }, "role": "reference_audio", "name": "audio1" } ] } ``` ### 4.5 Grok 视频系列 对外模型： - `grok-imagine-1.0-video` - `grok-imagine-video-1.5-preview` - `grok-video-3` 常用参数： - `prompt` - `ratio` / `aspect_ratio` - `resolution` / `size` - `seconds` / `duration` - `image` / `image_url` / `input_reference` - `reference_images` 示例： ```json { "model": "grok-imagine-1.0-video", "prompt": "雨夜霓虹街道上的电影感推镜，光影丰富，运动自然", "reference_images": [ "https://example.com/ref-1.jpg" ], "seconds": 10, "aspect_ratio": "16:9", "resolution": "720P" } ``` ### 4.6 Kling 视频主模型 对外主模型： - `kling-video` 必填： - `model` - `model_name` 支持的 `model_name`： - `kling-v1` - `kling-v1-5` - `kling-v1-6` - `kling-v2-master` - `kling-v2-1` - `kling-v2-1-master` - `kling-v2-5-turbo` - `kling-v2-6` - `kling-v3` 常见 `mode`： - `t2v` - `i2v` - `multi_i2v` - `extend` 最小入参： - 文生视频：`model + model_name + prompt + mode=t2v` - 图生视频：`model + model_name + prompt + mode=i2v + image` - 多图参考：`model + model_name + prompt + mode=multi_i2v + image_list` - 视频延长：`model + model_name + mode=extend + video_id` 示例： ```json { "model": "kling-video", "model_name": "kling-v2-6", "mode": "t2v", "prompt": "海边日落镜头，电影感，风吹长发", "duration": 5, "aspect_ratio": "16:9" } ``` ### 4.7 MiniMax / Hailuo 视频系列 对外模型： - `minimax-h3` - `hailuo-2.3` 建议： - `minimax-h3` 支持文生视频、图片参考和音频参考，推荐通过 `content` 混排文本与素材；也可使用 `image_urls`、`audio_urls` 等兼容字段。 - `hailuo-2.3` 需要首帧图片，推荐在 `content` 中传 `role=first_frame` 的 `image_url` 项，或使用 `image_urls` 传首帧图片。 - `minimax-h3` 常用 `duration=5~15`、`resolution=1440p`；`hailuo-2.3` 常用 `duration=6` 或 `10`、`resolution=768p`。 `minimax-h3` 示例： ```json { "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", "aspect_ratio": "16:9", "generate_audio": true } ``` `hailuo-2.3` 示例： ```json { "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", "aspect_ratio": "16:9" } ``` - `mode=t2v` - 最小入参：`model + prompt` - `mode=i2v` - 最小入参：`model + prompt + image_url` - `mode=i2v_first_last` - 最小入参：`model + prompt + image_url + end_image_url` - `mode=reference_images` - 最小入参：`model + prompt + reference_images` - `mode=reference_material` - 最小入参：`model + prompt + (image_urls/video_urls/audio_urls 至少一种)` ### Gemini Omni 调用说明 - `gemini-omni` 是 new-api 对外公开的视频模型名，可直接走 `POST /v1/videos`。 - `mode=t2v`：文生视频，最小入参为 `model + prompt`。 - `mode=r2v`：参考图/参考素材生成，图片可放在 `image`、`image_url`、`images`、`image_urls`、`reference_images`、`input_reference` 或 `content` 中。 - `mode=edit`：视频编辑，视频可放在 `video`、`video_url`、`videos` 或 `content` 中，也可同时传参考图。 - 时长字段可用 `seconds` 或 `duration`，会自动匹配到 4 / 6 / 8 / 10 秒档。 operationId: createVideo parameters: [] requestBody: required: true content: application/json: schema: type: object properties: model: type: string description: 必填，对外模型名。 `gemini-omni` 可通过 `/v1/videos` 调用。 enum: - sora-2 - sora-2-pro - gemini-omni - happyhorse-1.0 - happyhorse-1.0-i2v - happyhorse-1.0-t2v - happyhorse-1.0-r2v - happyhorse-1.0-video-edit - 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 - veo3 - veo3-fast - veo3-fast-frames - veo3-frames - veo3-pro - veo3-pro-frames - veo3.1 - veo3.1-4k - veo3.1-components - veo3.1-fast - veo3.1-pro - veo3.1-pro-4k - kling-video - grok-imagine-1.0-video - grok-imagine-video-1.5-preview - grok-video-3 - minimax-h3 - hailuo-2.3 - viduq3-turbo example: sora-2 prompt: type: string description: 统一提示词入口。大多数模型必填。 image: type: string format: binary description: 单图入口，部分兼容模式会映射到 images。 duration: type: integer description: 统一时长入口，部分模型也接受 seconds。 width: type: integer example: 512 description: Video width height: type: integer example: 512 description: Video height fps: type: integer example: 30 description: Video frame rate seed: type: integer example: 20231234 description: Random seed 'n': type: integer example: 1 description: Number of videos to generate response_format: type: string example: url description: Response format user: type: string example: user-1234 description: User identifier metadata: type: object additionalProperties: true description: 动态扩展字段容器。大量模型特有字段从这里反序列化。 mode: type: string description: 可选，视频生成模式。 `gemini-omni` 支持 `t2v`、`r2v`、`edit`。 images: type: array description: 统一多图入口。Vidu、Seedance、Veo 等会使用。 items: type: string content: type: array items: type: object additionalProperties: true size: type: string description: 统一尺寸入口，会映射为 resolution/aspect_ratio 等。 seconds: type: string description: Sora 兼容入口，运行时会回退到 duration。 input_reference: type: string description: Sora/Veo 兼容参考图入口，可为 multipart 文件或兼容对象。 parameters: type: object additionalProperties: true required: - model - prompt examples: openai_i2v_json: summary: OpenAI Sora i2v (application/json) value: size: 1280x720 images: - https://example.png model: sora-2 prompt: this is an example duration: 12 fps: '24' seed: '20231024' mode: i2v openai_i2v_input_reference: summary: OpenAI i2v (input_reference) value: model: sora-2 prompt: A cinematic drone shot over snowy mountains at sunrise input_reference: image_url: https://example.com/input.jpg seconds: '8' size: 1280x720 response_format: url openai_alias_compat: summary: Alias兼容 (image_url/duration/aspect_ratio) value: model: sora-2 prompt: A cinematic drone shot over snowy mountains at sunrise image_url: https://example.com/input.jpg duration: '8' aspect_ratio: '16:9' response_format: url gemini_omni_sora_t2v: summary: Gemini Omni Sora t2v value: model: gemini-omni mode: t2v prompt: A cinematic product video with smooth camera motion duration: 8 size: 1280x720 gemini_omni_sora_r2v: summary: Gemini Omni Sora 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_sora_edit: summary: Gemini Omni Sora 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 happyhorse_sora_t2v: summary: HappyHorse Sora t2v value: model: happyhorse-1.0 mode: t2v content: - type: text text: >- A cinematic white horse running through a neon city street duration: 5 resolution: 720P ratio: '16:9' happyhorse_sora_i2v: summary: HappyHorse Sora i2v value: model: happyhorse-1.0 mode: i2v content: - type: text text: The camera slowly pushes in, natural motion - type: image_url image_url: https://example.com/first-frame.jpg duration: 5 resolution: 720P happyhorse_sora_r2v: summary: HappyHorse Sora r2v value: size: 720x1280 model: happyhorse-1.0 mode: r2v prompt: this is an example duration: 15 content: - type: text text: this is an example - type: image_url image_url: url: https://example.png role: reference_image name: image1 parameters: resolution: 720P ratio: '9:16' duration: 15 seed: 1 happyhorse_sora_video_edit: summary: HappyHorse Sora video_edit value: model: happyhorse-1.0 mode: video_edit content: - type: text text: >- Change the jacket to a striped sweater and keep the motion natural - type: video_url video_url: https://example.com/input.mp4 - type: image_url image_url: https://example.com/reference.jpg resolution: 720P seedance_i2v_first: summary: Seedance i2v_first value: model: doubao-seedance-1-0-lite-i2v-250428 mode: i2v_first prompt: A panda skateboarding in a city street, cinematic image_urls: - https://example.com/first.jpg seconds: '5' size: 1280x720 seedance_i2v_first_last: summary: Seedance i2v_first_last value: model: doubao-seedance-1-0-lite-i2v-250428 mode: i2v_first_last prompt: A camera moves from first frame to last frame naturally image_urls: - https://example.com/first.jpg end_image_url: https://example.com/last.jpg seconds: '5' size: 1280x720 seedance_reference_images: summary: Seedance reference_images value: model: doubao-seedance-1-0-lite-i2v-250428 mode: reference_images prompt: Stylized short video keeping character consistency reference_images: - https://example.com/ref-1.jpg - https://example.com/ref-2.jpg seconds: '5' size: 1280x720 seedance_reference_material: summary: Seedance 全能参考模式(reference_material) value: model: doubao-seedance-1-0-lite-i2v-250428 mode: reference_material prompt: >- Blend image and short reference video into a coherent cinematic clip reference_images: - https://example.com/ref-1.jpg - https://example.com/ref-2.jpg video_urls: - https://example.com/ref-video.mp4 audio_urls: - https://example.com/ref-audio.mp3 seconds: '5' size: 1280x720 seedance_volc_content: summary: Seedance 火山方舟 content 模式 value: size: 1280x720 model: doubao-seedance-2-0-fast-260128 prompt: this is an example duration: 15 fps: '24' seed: '20231024' mode: reference_material content: - type: text text: this is an example - type: image_url image_url: url: https://example.png role: reference_image name: image1 - type: audio_url audio_url: url: https://example.mp3 role: reference_audio name: audio1 veo_first_last_frame: summary: Veo 首尾帧模式 value: model: veo3.1-fast prompt: >- A smooth transition from first frame to last frame, cinematic motion image_urls: - https://example.com/first-frame.jpg end_image_url: https://example.com/last-frame.jpg seconds: '8' size: 1280x720 veo_reference_images_1to3: summary: Veo 1~3张参考图模式 value: model: veo3.1-fast prompt: >- Use reference style and character consistency for a short ad clip reference_images: - https://example.com/ref-1.jpg seconds: '8' size: 1280x720 kling_text2video: summary: Kling 文生视频 value: model: kling-video prompt: A cat playing piano in the garden duration: 5 size: 1280x720 metadata: negative_prompt: blurry, low quality mode: std kling_image2video: summary: Kling 图生视频 value: model: kling-video prompt: A cat playing piano in the garden image: https://example.com/input.jpg duration: 5 size: 1280x720 metadata: negative_prompt: blurry, low quality mode: std grok_reference_video: summary: Grok 视频模式 value: model: grok-imagine-1.0-video prompt: A dramatic cinematic shot with fast motion and rich lighting reference_images: - https://example.com/ref-1.jpg seconds: 10 aspect_ratio: '16:9' resolution: 720P minimax_h3_sora_reference: summary: MiniMax H3 多素材视频 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 aspect_ratio: '16:9' generate_audio: true hailuo_2_3_sora_first_frame: summary: Hailuo 2.3 首帧图生视频 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 aspect_ratio: '16:9' vidu_sora_t2v: summary: Vidu Sora t2v value: model: viduq3-turbo mode: t2v content: - type: text text: A stylish product ad clip with cinematic lighting duration: 5 resolution: 720p aspect_ratio: '16:9' vidu_sora_i2v: summary: Vidu Sora i2v value: model: viduq3-turbo mode: i2v content: - type: text text: A stylish ad clip from a product still image - type: image_url image_url: https://example.com/product.jpg duration: 5 resolution: 720p vidu_sora_first_last: summary: Vidu Sora i2v_first_last value: model: viduq3-turbo mode: i2v_first_last content: - type: text text: A smooth shot from start frame to end frame - type: image_url image_url: https://example.com/start.jpg - type: image_url image_url: https://example.com/end.jpg duration: 5 resolution: 720p vidu_sora_reference: summary: Vidu Sora reference_images value: model: viduq3-turbo mode: reference_images content: - type: text text: Maintain product style and character consistency - type: image_url image_url: https://example.com/ref-1.jpg - type: image_url image_url: https://example.com/ref-2.jpg - type: image_url image_url: https://example.com/ref-3.jpg duration: 5 resolution: 720p aspect_ratio: '16:9' hailuo_text2video: summary: Hailuo 2.3 首帧图生视频 value: model: hailuo-2.3 prompt: A cinematic travel shot over the coastline image_urls: - https://example.com/first-frame.jpg duration: 6 resolution: 768p aspect_ratio: '16:9' responses: '200': description: 成功创建视频任务 content: application/json: schema: type: object properties: id: type: string task_id: type: string description: 兼容旧接口 待废弃 object: type: string model: type: string status: type: string description: >- Should use VideoStatus constants: VideoStatusQueued, VideoStatusInProgress, VideoStatusCompleted, VideoStatusFailed enum: - queued - in_progress - completed - failed - video_url - url - completed_at progress: type: integer created_at: type: integer completed_at: type: integer expires_at: type: integer seconds: type: string size: type: string remixed_from_video_id: type: string error: type: object metadata: type: object additionalProperties: true output: type: object request_id: type: string required: - created_at - id - model - object - progress - status example: id: video_abc123 object: video model: sora-2 status: queued progress: 0 created_at: 1764347090922 seconds: '8' headers: {} '400': description: 请求参数错误 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: {} deprecated: false security: - BearerAuth: [] components: schemas: ErrorResponse: type: object properties: error: type: object properties: message: type: string description: 错误信息 type: type: string description: 错误类型 param: type: string description: 相关参数 nullable: true code: type: string description: 错误代码 nullable: true securitySchemes: BearerAuth: type: http scheme: bearer description: |- 使用 Bearer Token 认证。 格式: `Authorization: Bearer sk-xxxxxx` ````