--- title: "Produce a video from reference images and videos with Seedance 2.5" method: POST path: "/v2/video/generate/seedance-2-5-reference-to-video" tags: ["video-generate"] --- # Produce a video from reference images and videos with Seedance 2.5 `POST /v2/video/generate/seedance-2-5-reference-to-video` Produce a video from a text prompt and reference media with Seedance 2.5. The prompt addresses the references by position: the first reference image is `[Image1]`, the second `[Image2]`, the first reference video is `[Video1]`, and so on. Supply reference images either as `reference_image_asset_identifiers` (images already stored with Ideogram) or as raw `reference_images` bytes (multipart requests only); supplying both is rejected, and uploaded bytes are used for this request only and are not stored as an asset. Supply reference videos as `reference_video_asset_identifiers`, which can reference uploaded or generated videos. At most 9 reference images and 10 reference videos are accepted, and reference videos are capped again on clip length: each clip must be between 2 and 30 seconds long, and the clips must total no more than 30 seconds. Supply up to 10 MP3/WAV `reference_audios` as multipart files, at most 15 MB each. Each audio clip must be 2–30 seconds, with at most 30 seconds total. Reference them as `[Audio1]`, `[Audio2]`, and so on. Audio is used for this request only. At least one reference image or video is required: the model conditions every generation on the media it is given, so a request with no references is rejected. Video generation always runs asynchronously: the response returns as soon as the request is accepted and carries only a `generation_id`. Poll for completion and results with `GET /v1/generations/{generation_id}` using that id, or supply a `webhook_url` to have the finished result POSTed to your server instead. Video links are available for a limited period of time; download the video if you want to keep it. ## Query parameters - `dry_run` boolean ## Request body - GenerateVideoSeedDance25ReferenceToVideoRequest — Request body for Seedance 2.5 reference-to-video. The prompt addresses references by position — `[Image1]`, `[Video1]`, and so on. Reference images arrive either as `reference_image_asset_identifiers` or (multipart requests only) as raw `reference_images` bytes, never both. Reference videos arrive only as `reference_video_asset_identifiers`, which may reference uploaded or generated videos. At least one reference image or video is required. - `prompt` string, required — A natural-language prompt describing the video to produce. Reference media is addressed by position, as in "[Image1] walks toward the camera with the motion of [Video1]". - `reference_image_asset_identifiers` AssetIdentifier[] — Images already stored with Ideogram to use as references, by reference, in prompt order. Cannot be combined with `reference_images`. Only image assets are accepted. - `asset_type` 'ASSET' | 'CANVAS_ASSET' | 'LAYERED_ASSET' | 'RESPONSE' | 'UPLOAD', required - `asset_id` string, required - `reference_images` string[] — Images to use as references (max size 50MB each), as raw bytes, in prompt order; only common image formats such as JPEG, PNG, and WEBP are supported. Multipart requests only. Cannot be combined with `reference_image_asset_identifiers`. The bytes are used for this request only and are not stored as an asset. - `reference_video_asset_identifiers` AssetIdentifier[] — Uploaded or generated videos to use as references, by reference, in prompt order. Each clip must be between 2 and 30 seconds long, and the clips must total no more than 30 seconds. Upload video files first and pass their asset identifiers. - `asset_type` 'ASSET' | 'CANVAS_ASSET' | 'LAYERED_ASSET' | 'RESPONSE' | 'UPLOAD', required - `asset_id` string, required - `reference_audios` string[] — MP3 or WAV audio references, in prompt order. Multipart requests only. Each file must be at most 15 MB and between 2 and 30 seconds; combined duration must not exceed 30 seconds. At least one reference image or video is required. Audio is used for this generation only and is not saved to your library. - `aspect_ratio` 'auto' | '21x9' | '16x9' | '4x3' | '1x1' | '3x4' | '9x16' — The aspect ratio of the generated video. `AUTO` lets the model choose the most suitable ratio from the prompt; any other value pins the ratio. - `resolution` '480p' | '720p' | '1080p' — The resolution tier of the generated video. - `duration` integer — The length of the generated video in seconds. When omitted, the model picks the best duration for the prompt ("auto"). - `generate_audio` boolean — Whether to generate an audio track for the video. Audio roughly doubles the provider cost and is subject to stricter output moderation. - `webhook_url` string, uri — HTTPS URL that Ideogram delivers the generated result to. Ideogram sends a JSON POST to this URL once all images for the request have finished generating. The body mirrors the synchronous generate response: `request_id`, `created`, and a `data` array containing every generated image (`url`, `prompt`, `resolution`, `seed`, `is_image_safe`). Each delivery is signed with Ed25519 and verifiable against the public keys at `https://api.ideogram.ai/v1/.well-known/jwks.json`. Must be HTTPS; private and loopback hosts and the cloud metadata service are rejected. - `private` boolean, nullable — When true or omitted, the output is kept private to your account. Set to false to publish the output to the public feed. Enterprise accounts always generate privately. - `target_collection_id` string — A collection you can write to, by its URL-safe base64 collection id. The output videos are added to it when the request completes. ## Response `200` An acknowledgement to poll with `GET /v1/generations/{generation_id}`. - GenerateVideoSeedDance25Response — Acknowledgement returned by the Seedance 2.5 video generation endpoints. Video generation always runs asynchronously, so the generated video is never part of this response: poll for it with `GET /v1/generations/{generation_id}` using the returned `generation_id`, or receive it at the `webhook_url` you supplied. - `generation_id` string, required — URL-safe base64 ID of the accepted generation. Accepted by the `GET /v1/generations/{generation_id}` polling endpoint. - `created` string, date-time, required — The time the request was accepted. ## Other responses - `400` — Invalid input provided. - `401` — Unauthorized. - `402` — Insufficient credits or quota. - `403` — This account does not have access to this model. - `404` — A referenced asset was not found. - `422` — The prompt did not pass safety checks. - `429` — Too many requests. - `500` — Internal server error. - `503` — The endpoint is temporarily unavailable. ## Changes - **2026-09-19** `4e95197be44a` — 2 breaking, 4 info - removed the enum value `AUTO` of the request property `aspect_ratio` (media type: multipart/form-data) - removed the enum value `AUTO` of the request property `aspect_ratio` (media type: application/json) - the `aspect_ratio` request property default value changed from `AUTO` to `auto` (media type: multipart/form-data) - the `aspect_ratio` request property default value changed from `AUTO` to `auto` (media type: application/json) - …2 more - **2026-09-17** `9d3ff2d98e27` — 2 info - added the new optional request property `reference_audios` (media type: multipart/form-data) - added the new optional request property `reference_audios` (media type: application/json) - **2026-09-16** `a235a15c0235` — 1 info - endpoint added [Change history](https://skmtc.dev/ideogram/apis/ideogram-openapi-3-0/changes/v2/video/generate/seedance-2-5-reference-to-video/post.md) --- [API](https://skmtc.dev/ideogram/apis/ideogram-openapi-3-0.md) · [All operations](https://skmtc.dev/ideogram/apis/ideogram-openapi-3-0/llms.txt) · [OpenAPI document](https://skmtc.dev/ideogram/apis/ideogram-openapi-3-0/revisions/4e95197be44a?raw)