Generate Assets
Use the POST /api/v1/generate endpoint to create 3D models, ASCII art, animations, and standalone images from text prompts.
Endpoint
All generation requests use the same endpoint. The mode field determines which asset type is created. Every request needs an Authorization: Bearer mr_live_... header - create a key on the API Keys page.
Generation runs asynchronously: POST starts the job and returns immediately with a generation id and status: "pending" - credits are charged up front (and refunded automatically if generation fails). Poll GET /api/v1/generate/{id} until status becomes "complete" (or "failed") to get the finished asset.
status moves through mode-specific intermediate values (e.g. enhancing, generating_image, generating_3d) before reaching complete.
3D Models5 CREDITS
Generate textured 3D meshes from a text description. Output is a GLB file ready for web viewers, game engines, or AR applications.
Request Body
| Parameter | Type | Required | Description |
|---|---|---|---|
| mode | string | YES | Set to "trellis" |
| prompt | string | YES | Text description of the 3D model |
| meshSimplify | number | No | Simplification ratio 0-1 (default 0.95) |
| textureSize | number | No | 512, 1024, or 2048 (default 1024) |
Example Request
All fields are top-level on the request body - there is no nested options object.
Example Response
Returned immediately - see Endpoint above for how to poll for the finished model.
ASCII Art1 CREDIT
Generate animated ASCII art frames from a prompt. Returns an array of text frames that can be played back sequentially for terminal-style animations.
Request Body
| Parameter | Type | Required | Description |
|---|---|---|---|
| mode | string | YES | Set to "ascii" |
| prompt | string | YES | Text description of the ASCII art |
Example Request
Example Response
Returned immediately - see Endpoint above for how to poll for the finished frames.
Animations1 CREDIT
Create animated pixel-art loops from a text prompt. Configure frame count, art style, animation type, and background transparency for game-ready assets.
Request Body
| Parameter | Type | Required | Description |
|---|---|---|---|
| mode | string | YES | Set to "animation" |
| prompt | string | No* | Text description of the animation subject |
| referenceImage | string | No* | A data:image/... data URL to match the character's look across frames - works with or without prompt (leave prompt blank and it's auto-described; add one to guide the pose/motion) |
| frameCount | number | No | Number of frames (default 8) |
| artStyle | string | No | "pixel-art", "hand-drawn", etc. |
| animationType | string | No | "idle", "walk", "attack", etc. |
| background | string | No | "transparent" or "white" |
| variations | number | No | 1-10 (default 1). Runs the request that many times and charges 1 credit per variation; the response returns an ids array to poll, one per variation |
* At least one of prompt or referenceImage is required - not both, though combining them works too.
Example Request
Example Response
Returned immediately - see Endpoint above for how to poll for the finished animation.
Images1 CREDIT
Generate a single standalone AI image from a text prompt - useful for illustrations, concept art, thumbnails, or any general-purpose image that isn't a 3D model, ASCII art, or animation.
Request Body
| Parameter | Type | Required | Description |
|---|---|---|---|
| mode | string | YES | Set to "image" |
| prompt | string | YES | Text description of the image |
Example Request
Example Response
Returned immediately - see Endpoint above for how to poll for the finished image.
Full Parameters Reference
| Parameter | Type | Modes | Description |
|---|---|---|---|
| mode | string | all | Generation mode: "trellis", "ascii", "animation", "image", or "img-to-3d" |
| prompt | string | all except img-to-3d | Text description of the asset to generate |
| meshSimplify | number (0-1) | trellis | Mesh simplification ratio |
| textureSize | 512 | 1024 | 2048 | trellis | Texture resolution in pixels |
| sourceImage | string (data URL) | img-to-3d | Source image to convert into a 3D model - required for this mode |
| frameCount | number | animation | Number of animation frames |
| artStyle | string | animation | Art style (pixel-art, hand-drawn, etc.) |
| animationType | string | animation | Animation type (idle, walk, attack, etc.) |
| background | string | animation | "transparent" or "white" |
| referenceImage | string (data URL) | animation | Reference image to match the character’s look across frames - can be combined with prompt |
| variations | number (1-10) | animation, image, ascii | Generate this many results from one request, charged 1 credit each. The response then carries an ids array - one generation to poll per variation |
| isPrivate | boolean | all | Keep the generated asset out of the public gallery (default false) |