> ## Documentation Index > Fetch the complete documentation index at: https://docs.apipod.ai/llms.txt > Use this file to discover all available pages before exploring further. # Seedance 2.0 Fast > All-in-one Seedance 2.0 Fast: one model ID covers every scenario at Fast-tier speed, with the scenario inferred from your request materials. ## OpenAPI ````yaml api-reference/openapi/seedance--seedance-2-0-fast.yaml POST /v1/videos/generations openapi: 3.1.0 info: title: Seedance 2.0 Fast API version: 1.0.0 description: >- Seedance 2.0 Fast is the all-in-one model of the Fast tier: one public model ID covers every scenario at Fast-tier speed. Prompt-only requests are text-to-video, 1-2 images in image_urls are image-to-video with first/last frame control, and reference_images, reference videos, or reference audios select omni reference generation, with synchronized audio and 480p / 720p output. In APIPod, the public model ID is seedance-2.0-fast. It accepts up to 9 reference images, 3 reference videos, and 3 reference audios, with durations from 4 to 15 seconds, and returns results through asynchronous video tasks. This is a full-capability variant where media URLs are submitted to the asset review service before the task is created by default (real_person=true); set real_person=false only when the materials are confirmed face-free to pass media URLs through without review, and plain public URLs always work in requests. servers: - url: https://api.apipod.ai description: Production security: [] paths: /v1/videos/generations: post: tags: - Seedance 2.0 Fast summary: Create Generation Task description: >- Seedance 2.0 Fast is the all-in-one model of the Fast tier: one public model ID covers every scenario at Fast-tier speed. Prompt-only requests are text-to-video, 1-2 images in image_urls are image-to-video with first/last frame control, and reference_images, reference videos, or reference audios select omni reference generation, with synchronized audio and 480p / 720p output. In APIPod, the public model ID is seedance-2.0-fast. It accepts up to 9 reference images, 3 reference videos, and 3 reference audios, with durations from 4 to 15 seconds, and returns results through asynchronous video tasks. This is a full-capability variant where media URLs are submitted to the asset review service before the task is created by default (real_person=true); set real_person=false only when the materials are confirmed face-free to pass media URLs through without review, and plain public URLs always work in requests. operationId: create-seedance-2-0-fast requestBody: required: true content: application/json: schema: type: object title: Seedance 2.0 Fast properties: model: type: string title: Model ID description: Public APIPod model ID. const: seedance-2.0-fast prompt: type: string title: Prompt description: >- Generation or editing instructions, up to 30000 characters. It is recommended to keep the prompt to no more than 500 Chinese characters or 1,000 English words. Lengthy text will lead to scattered information, and the model may ignore details and only focus on key points, resulting in missing elements in the generated video. maxLength: 30000 image_urls: type: array title: Image Urls description: >- Image URLs. Scenario inference applies: when images are the only media input and 1-2 URLs are provided they are treated as first/last frames (image-to-video); with other reference media present or more than 2 URLs, all images are treated as reference images. Pair with the role field to pin the semantics explicitly. Up to 9 images are supported; each image must be smaller than 30 MB. maxItems: 9 items: type: string role: type: string title: Role description: >- Explicit interpretation of image_urls. reference_images: all images are treated as reference images regardless of count. first_last_frame: images are treated as the first frame plus an optional last frame (max 2; cannot be combined with reference videos, audios, or reference_images). When omitted, the scenario is inferred from the materials. enum: - reference_images - first_last_frame reference_images: type: array title: Reference Images description: >- Explicit reference image URLs. Always treated as reference images (omni reference generation) regardless of count; use this field when you need strict reference semantics with few images. Up to 9 images are supported; each image must be smaller than 30 MB. maxItems: 9 items: type: string video_urls: type: array title: Video Urls description: >- Reference video URLs. Up to 3 videos are supported; each video lasts 2-15 seconds and the total duration of all videos must not exceed 15 seconds. maxItems: 3 items: type: string audio_urls: type: array title: Audio Urls description: >- Reference audio URLs. Up to 3 audios are supported; each audio lasts 2-15 seconds and the total duration of all audios must not exceed 15 seconds. Audio cannot be used alone; include at least one image or video reference. maxItems: 3 items: type: string duration: type: integer title: Duration description: Video duration in seconds, from 4 to 15. enum: - 4 - 5 - 6 - 7 - 8 - 9 - 10 - 11 - 12 - 13 - 14 - 15 default: 5 minimum: 4 maximum: 15 resolution: type: string title: Resolution description: Generate video resolution. enum: - 480p - 720p default: 720p aspect_ratio: type: string title: Aspect Ratio description: >- Aspect ratio of the generated video. When the ratio is configured as adaptive, the model will automatically adapt the aspect ratio according to the generation scenario. enum: - adaptive - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' - '21:9' default: adaptive generate_audio: type: boolean title: Generate Audio description: >- Controls whether the generated video contains audio synchronized with the visuals. default: true return_last_frame: type: boolean title: Retrun Last Frame description: >- Whether to return the last frame image of the generated video. Using this parameter enables the generation of multiple consecutive videos: taking the last frame of the previous generated video as the first frame of the next video task. default: false watermark: type: boolean title: Watermark description: Add the upstream watermark. default: false web_search: type: boolean title: Web Search description: >- Allow retrieving live information when the channel supports it. default: false real_person: type: boolean title: Real Person description: >- Whether the reference materials contain real people (human faces). Defaults to true: materials are submitted to the asset review service before task creation. Set to false only when the materials are confirmed face-free to skip review and pass material URLs through as-is. default: true required: - model - prompt example: model: seedance-2.0-fast prompt: >- Quick concept pass: astronaut walking on the moon at sunrise, 5 seconds. image_urls: - https://example.com/first.png duration: 5 resolution: 720p aspect_ratio: adaptive generate_audio: true responses: '200': description: Task accepted content: application/json: schema: type: object title: Task Submit Response description: Standard response for task submission properties: code: type: integer data: type: object title: Task Submit Data description: Data content for task submission properties: task_id: type: string description: generatation task id message: type: string required: - code - message - data example: code: 200 message: success data: task_id: vid_task_01JEXAMPLE security: - bearerAuth: [] x-codeSamples: - lang: Shell label: cURL source: |- curl https://api.apipod.ai/v1/videos/generations \ -H "Authorization: Bearer $APIPOD_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "seedance-2.0-fast", "prompt": "Quick concept pass: astronaut walking on the moon at sunrise, 5 seconds.", "image_urls": ["https://example.com/first.png"], "duration": 5, "resolution": "720p", "aspect_ratio": "adaptive", "generate_audio": true }' - lang: Python label: Python source: |- import os import requests payload = { "model": "seedance-2.0-fast", "prompt": "Quick concept pass: astronaut walking on the moon at sunrise, 5 seconds.", "image_urls": ["https://example.com/first.png"], "duration": 5, "resolution": "720p", "aspect_ratio": "adaptive", "generate_audio": True } response = requests.post( "https://api.apipod.ai/v1/videos/generations", headers={ "Authorization": f"Bearer {os.environ['APIPOD_API_KEY']}", "Content-Type": "application/json", }, json=payload, timeout=60, ) response.raise_for_status() print(response.json()) components: securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: APIPod API key description: Use your APIPod API key as a Bearer token in the Authorization header. ````