Seedance 2.0 Fast Video Generation

Describe a scene in everyday words to request a Seedance 2.0 Fast video. You can also share a photo or video link if your AI assistant can open it; a sound clip must come with a photo or video.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use Toolmu's Seedance 2.0 Fast video tool for this request. I may describe one scene in words or share a photo, video or sound link. Use a link only if you can open it; if you cannot, ask me for a text description or another link. A sound clip must be used with a photo or video. Turn everyday requests such as [horizontal video] and [about 5 seconds] into choices this tool supports, and ask me if something cannot be used. Before any action that could cost money, tell me the current price and wait for my approval. Follow the task until it finishes or fails, and report only what it actually returns. Do not promise exact reproduction, completion time or that a returned link will open.

Task:
Turn the photo at [a photo share link] into a [horizontal video] about [5 seconds] long, showing [a paper boat drifting slowly across a puddle]. If you cannot open the photo, ask me to describe the scene instead.

Paste into your connected AI's conversation.

Connection guide

Up to 120 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

ByteDance

Seedance 2.0 Fast Video Generation

Describe a scene in everyday words to request a Seedance 2.0 Fast video. You can also share a photo or video link if your AI assistant can open it; a sound clip must come with a photo or video.

You receive

This Tool sends a Seedance 2.0 Fast video request from a scene description or reference media. After successful completion, your AI assistant can show you the actual result returned.

Start with your task

Turn the photo at [a photo share link] into a [horizontal video] about [5 seconds] long, showing [a paper boat drifting slowly across a puddle]. If you cannot open the photo, ask me to describe the scene instead.

What to know

A submitted request is not a finished video. The video service may not be able to open a link, and exact reproduction or completion time is not guaranteed. A sound clip used as a guide must come with a photo or video.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Video request`body`	`object`	Required	Required request object containing at least one content item and any chosen video settings. Required fields `content`
Aspect ratio`body.ratio`	`string`	Optional	Choose 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 or adaptive. Use 9:16 for a vertical composition; adaptive requests a suitable ratio chosen during generation. Options `16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive`
Prompt and reference items`body.content`	`array`	Required	Required list with at least one item. Each item is text, an image URL, a video URL or an audio URL. Audio references must accompany at least one image or video. Minimum items `1`
One content item`body.content[]`	`object`	—	Choose one content type and provide its matching text or media URL object. The fields needed depend on that item type.
Scene description`body.content[].text`oneOf · 1	`string`	—	For a text item, describe the subject, movement, setting and camera. Supply 1–6000 characters. Refer to ordered media as @Image1, @Video1 or @Audio1 and say what each contributes. Minimum length `1` Maximum length `6000`
Content type`body.content[].type`oneOf · 1	`string`	—	Use text, image_url, video_url or audio_url to select the corresponding item shape. This type is required within each item. Fixed value `text`
Reference role`body.content[].role`oneOf · 2	`string`	—	For images, choose first_frame, last_frame or reference_image; include a first frame when using a last frame. Use up to 9 reference images. Video uses reference_video and audio uses reference_audio. Supply up to 3 clips per type, each 2–15 seconds and no more than 15 seconds total per type. Roles guide intended use, not an exact visual or audio match. Options `first_frame, last_frame, reference_image`
Content type`body.content[].type`oneOf · 2	`string`	—	Use text, image_url, video_url or audio_url to select the corresponding item shape. This type is required within each item. Fixed value `image_url`
Image reference`body.content[].image_url`oneOf · 2	`object`	—	For an image item, provide an object containing its URL. Use a first or last frame for the intended opening or ending, or a reference image for appearance/style guidance. Required fields `url`
Image address`body.content[].image_url.url`oneOf · 2	`string`	—	Nonempty URL string for an image you want to supply. Ensure the image is accessible and suitable for the intended reference role. Minimum length `1`
Reference role`body.content[].role`oneOf · 3	`string`	—	For images, choose first_frame, last_frame or reference_image; include a first frame when using a last frame. Use up to 9 reference images. Video uses reference_video and audio uses reference_audio. Supply up to 3 clips per type, each 2–15 seconds and no more than 15 seconds total per type. Roles guide intended use, not an exact visual or audio match. Fixed value `reference_video`
Content type`body.content[].type`oneOf · 3	`string`	—	Use text, image_url, video_url or audio_url to select the corresponding item shape. This type is required within each item. Fixed value `video_url`
Video reference`body.content[].video_url`oneOf · 3	`object`	—	For a video item, provide an object containing the reference clip URL. Describe which motion or visual details should guide the new video. Required fields `url`
Video address`body.content[].video_url.url`oneOf · 3	`string`	—	Nonempty URL string for the reference video. Check the clip is accessible and meets the reference duration conditions. Minimum length `1`
Reference role`body.content[].role`oneOf · 4	`string`	—	For images, choose first_frame, last_frame or reference_image; include a first frame when using a last frame. Use up to 9 reference images. Video uses reference_video and audio uses reference_audio. Supply up to 3 clips per type, each 2–15 seconds and no more than 15 seconds total per type. Roles guide intended use, not an exact visual or audio match. Fixed value `reference_audio`
Content type`body.content[].type`oneOf · 4	`string`	—	Use text, image_url, video_url or audio_url to select the corresponding item shape. This type is required within each item. Fixed value `audio_url`
Audio reference`body.content[].audio_url`oneOf · 4	`object`	—	For an audio item, provide an object containing the reference audio URL, with an image or video elsewhere in the content list. Describe what the sound should guide. Required fields `url`
Audio address`body.content[].audio_url.url`oneOf · 4	`string`	—	Nonempty URL string for the reference audio. Check accessibility and the reference duration conditions; an audio item alone is not enough. Minimum length `1`
Requested video length`body.duration`	`integer`	Optional	Choose a video length from 4 to 15 seconds. Set it explicitly when the length matters. Default `5` Minimum `4` Maximum `15`
Queue priority`body.priority`	`integer`	Optional	Choose an integer from 0 to 9 to request queue priority; higher values request higher priority, without guaranteeing a completion time. Minimum `0` Maximum `9`
AI watermark`body.watermark`	`boolean`	Optional	Set true to request an AI Generated watermark, or false to omit it. Default `false`
Requested resolution`body.resolution`	`string`	Optional	Choose 480p or 720p. Resolution also affects the pricing choice, so confirm the current applicable charge before generating. Default `720p` Options `480p, 720p`
Generate sound`body.generate_audio`	`boolean`	Optional	Choose whether to request synchronized generated sound. This is separate from supplying an audio reference; check the actual completed result for what was generated. Default `true`

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "content"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "ratio": {
          "enum": [
            "16:9",
            "4:3",
            "1:1",
            "3:4",
            "9:16",
            "21:9",
            "adaptive"
          ],
          "type": "string",
          "description": "Aspect ratio. Omit for the upstream default (adaptive - picks the best fit from your prompt/inputs)."
        },
        "content": {
          "type": "array",
          "items": {
            "oneOf": [
              {
                "type": "object",
                "required": [
                  "type",
                  "text"
                ],
                "properties": {
                  "text": {
                    "type": "string",
                    "maxLength": 6000,
                    "minLength": 1,
                    "description": "Text prompt describing the video (recommended <1000 words). Refer to your other content items by ordinal, numbered per type in array order: @Image1, @Image2, @Video1, @Audio1 - and say what each one supplies (appearance, motion, timbre) and what it should not. Mark sounds with () music, <> sound effects, {} dialogue, 【】 subtitles; prefix non-English dialogue with its language."
                  },
                  "type": {
                    "type": "string",
                    "const": "text"
                  }
                },
                "additionalProperties": false
              },
              {
                "type": "object",
                "required": [
                  "type",
                  "image_url"
                ],
                "properties": {
                  "role": {
                    "enum": [
                      "first_frame",
                      "last_frame",
                      "reference_image"
                    ],
                    "type": "string",
                    "description": "first_frame (image-to-video, default) pins the exact opening frame; last_frame (only with a first_frame) pins the closing one; reference_image (up to 9) is soft guidance for subject or style, not a frame."
                  },
                  "type": {
                    "type": "string",
                    "const": "image_url"
                  },
                  "image_url": {
                    "type": "object",
                    "required": [
                      "url"
                    ],
                    "properties": {
                      "url": {
                        "type": "string",
                        "minLength": 1
                      }
                    },
                    "additionalProperties": false
                  }
                },
                "additionalProperties": false
              },
              {
                "type": "object",
                "required": [
                  "type",
                  "video_url"
                ],
                "properties": {
                  "role": {
                    "type": "string",
                    "const": "reference_video",
                    "description": "Reference video (up to 3, each 2-15s, total <=15s) for multimodal generation, video editing, or extension."
                  },
                  "type": {
                    "type": "string",
                    "const": "video_url"
                  },
                  "video_url": {
                    "type": "object",
                    "required": [
                      "url"
                    ],
                    "properties": {
                      "url": {
                        "type": "string",
                        "minLength": 1
                      }
                    },
                    "additionalProperties": false
                  }
                },
                "additionalProperties": false
              },
              {
                "type": "object",
                "required": [
                  "type",
                  "audio_url"
                ],
                "properties": {
                  "role": {
                    "type": "string",
                    "const": "reference_audio",
                    "description": "Reference audio (up to 3, each 2-15s, total <=15s). Cannot be the only input - include at least one image or video."
                  },
                  "type": {
                    "type": "string",
                    "const": "audio_url"
                  },
                  "audio_url": {
                    "type": "object",
                    "required": [
                      "url"
                    ],
                    "properties": {
                      "url": {
                        "type": "string",
                        "minLength": 1
                      }
                    },
                    "additionalProperties": false
                  }
                },
                "additionalProperties": false
              }
            ]
          },
          "minItems": 1,
          "description": "Content items: text (text-to-video), image_url (image-to-video / first+last frame / reference images), video_url and audio_url (multimodal reference)."
        },
        "duration": {
          "type": "integer",
          "default": 5,
          "maximum": 15,
          "minimum": 4,
          "description": "Duration in seconds (4-15)."
        },
        "priority": {
          "type": "integer",
          "maximum": 9,
          "minimum": 0,
          "description": "Queue priority 0-9 (higher = front of the queue). Default 0."
        },
        "watermark": {
          "type": "boolean",
          "default": false,
          "description": "Add an \"AI Generated\" watermark. Default false."
        },
        "resolution": {
          "enum": [
            "480p",
            "720p"
          ],
          "type": "string",
          "default": "720p",
          "description": "Output resolution (also the price selector)."
        },
        "generate_audio": {
          "type": "boolean",
          "default": true,
          "description": "Generate synchronized audio (voice, sound effects, music). Default true. No price impact."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

Give each reference a clear role

When using several references, explain which supplies appearance, movement or sound, and how they should work together. Refer to them as @Image1, @Video1 or @Audio1, numbered separately within each media type in the order supplied. An audio reference needs at least one image or video alongside it.

For broader model-family updates, see the BytePlus model release announcements.

Seedance 2.0 Fast Video Generation

Seedance 2.0 Fast Video Generation

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Give each reference a clear role

Connect your AI assistant

Describe the video you want

Review the returned result