---
title: "Edit a previously generated spritesheet: re-prompt its underlying animation (edit_mode \"prompt\"), extend the frame beyond its borders (\"outpaint\"), or repair a bad loop (\"fix_loop\"). Pass the `spritesheet_url` you received from `animateSprite`, `transferMotion`, or an earlier edit - it must be a spritesheet you generated within the last 7 days; arbitrary external images are not accepted. A `prompt` is required for edit_mode \"prompt\", optional for \"outpaint\", and not accepted for \"fix_loop\"; optionally add up to 5 reference `images` (URL or base64) to guide the edit. Synchronous until September 10, 2026: the call blocks until the edited spritesheet is rendered and returns the same result shape as animateSprite (spritesheet URL, frame layout, optional GIF or individual frames). Credits are charged only on success, based on the produced duration and never more than the duration you requested. Pass an optional `request_id` to tag the result for later retrieval via `GET /assets/sprites/results`. Requires an API key (user scope). Async is the intended integration pattern: pass `async: true` and the call returns 202 with a job id - poll `GET /assets/jobs/{id}` (`getApiJob` in MCP), honouring poll_after_ms or long-polling with wait=30, until status is succeeded, whose result field is exactly the response documented for this operation. Synchronous responses are deprecated: they remain the default until September 10, 2026, after which requests default to async and return 202 with a job id; set `async: false` explicitly to keep synchronous behavior during and after the transition. Synchronous calls run on the same queue: the response carries an X-Ludo-Job-Id header, and a job still running after 15 minutes comes back as 202 with the job instead of an error. Each account may have up to 50 generations queued or running at once via the API; a request beyond that returns 429 (code PENDING_JOBS_LIMIT)."
method: POST
path: "/assets/sprite/edit"
tags: ["Spritesheets"]
---

# Edit a previously generated spritesheet: re-prompt its underlying animation (edit_mode "prompt"), extend the frame beyond its borders ("outpaint"), or repair a bad loop ("fix_loop"). Pass the \`spritesheet_url\` you received from \`animateSprite\`, \`transferMotion\`, or an earlier edit - it must be a spritesheet you generated within the last 7 days; arbitrary external images are not accepted. A \`prompt\` is required for edit_mode "prompt", optional for "outpaint", and not accepted for "fix_loop"; optionally add up to 5 reference \`images\` (URL or base64) to guide the edit. Synchronous until September 10, 2026: the call blocks until the edited spritesheet is rendered and returns the same result shape as animateSprite (spritesheet URL, frame layout, optional GIF or individual frames). Credits are charged only on success, based on the produced duration and never more than the duration you requested. Pass an optional \`request_id\` to tag the result for later retrieval via \`GET /assets/sprites/results\`. Requires an API key (user scope). Async is the intended integration pattern: pass \`async: true\` and the call returns 202 with a job id - poll \`GET /assets/jobs/{id}\` (\`getApiJob\` in MCP), honouring poll_after_ms or long-polling with wait=30, until status is succeeded, whose result field is exactly the response documented for this operation. Synchronous responses are deprecated: they remain the default until September 10, 2026, after which requests default to async and return 202 with a job id; set \`async: false\` explicitly to keep synchronous behavior during and after the transition. Synchronous calls run on the same queue: the response carries an X-Ludo-Job-Id header, and a job still running after 15 minutes comes back as 202 with the job instead of an error. Each account may have up to 50 generations queued or running at once via the API; a request beyond that returns 429 (code PENDING_JOBS_LIMIT).

`POST /assets/sprite/edit`

## Request body

- EditSpritesheetPayloadPublic — Payload for editing a previously generated spritesheet. edit_mode selects the operation - prompt-driven edit (default), outpaint, or loop fixing.
  - `spritesheet_url` string, required — URL of a spritesheet you generated in the last 7 days (returned by animateSprite, transferMotion, or a previous edit as spritesheet_url). External URLs are not accepted.
  - `edit_mode` 'prompt' | 'outpaint' | 'fix_loop' — Edit operation to perform.
  - `prompt` string — Edit instruction. Required for edit_mode "prompt", optional for "outpaint", not accepted for "fix_loop".
  - `images` string[] — Optional reference images (up to 5), each a URL or base64, to guide the edit.
  - `duration` number, float — Output animation length in seconds. Defaults to the source spritesheet's duration.
  - `model` 'forge' | 'forge-pixel' — Backing model. forge-pixel is the pixel-art variant, for spritesheets whose frames are pixel art.
  - `crop` boolean — Crop sprite frames to fit content. Results in smaller spritesheets but inconsistent frame sizes across different animations.
  - `loop` boolean — Trim the animation at the beginning or end to create a seamless loop.
  - `frames` 4 | 9 | 16 | 25 | 36 | 49 | 64 — Number of frames in the output spritesheet. Defaults to the source spritesheet's frame count.
  - `frame_size` 32 | 64 | 96 | 128 | 192 | 256 | 384 | 0 — Size of each frame in pixels (width and height). 0 is for maximum resolution. Defaults to the source spritesheet's frame size.
  - `gif` boolean — When true, generates an animated GIF from the spritesheet and returns it in gif_url. Disabled by default to reduce response time.
  - `individual_frames` boolean — When true, extracts each frame from the spritesheet as an individual image and returns the URLs in individual_frame_urls.
  - `spritesheet_with_background` boolean — When true, also returns the spritesheet with background intact (before background removal). The with-background spritesheet URL will be in spritesheet_with_background_url.
  - `request_id` string — Optional client-provided identifier, unique per request. Re-sending the same request_id returns the existing job instead of generating again. Also usable with the results endpoint.
  - `async` boolean — When true, return 202 immediately with a job id instead of waiting for the result. Poll GET /assets/jobs/{id}. Defaults to false (synchronous).

## Response `200`

Success

- SpriteResult
  - `spritesheet_url` string
  - `video_url` string
  - `audio_b64` string
  - `gif_url` string
  - `individual_frame_urls` string[]
  - `num_frames` integer
  - `num_cols` integer
  - `num_rows` integer
  - `spritesheet_with_background_url` string
  - `individual_frame_with_background_urls` string[]
  - `duration` number, float
  - `request_id` string
  - `created_at` integer

## Other responses

- `202` — Accepted - the generation was queued (async: true, or a synchronous call still running after 15 minutes). Poll GET /assets/jobs/{id}.
- `400` — Error

## Changes

- **2026-08-30** `a8a0b85d1839` — 1 info
  - added the success response with the status `202`

[Change history](https://skmtc.dev/ludo/apis/ludo-ai-api/changes/assets/sprite/edit/post.md)

---

[API](https://skmtc.dev/ludo/apis/ludo-ai-api.md) · [All operations](https://skmtc.dev/ludo/apis/ludo-ai-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/ludo/ludo-ai-api/revisions/37a21589e770/schema)