> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Luma Labs

> Create and manage AI image and video generations and reusable files through the current Luma Agents API.

![Luma Labs logo](https://mintcdn.com/composio-preview/ufpARLIsio16odJB/images/toolkits/luma_labs.svg?fit=max\&auto=format\&n=ufpARLIsio16odJB\&q=85\&s=fe1699c4f79a25cc0bc354473bd747d4)

* **Category:** media generation
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 11
* **Triggers:** 0
* **Slug:** `LUMA_LABS`
* **Version:** 20261030\_00
* **Instant:** Supported on the latest version. Support varies by tool.

## Tools

> [accordion] Delete File
>
> **Slug:** `LUMA_LABS_DELETE_FILE`
>
> Soft-delete a Luma file so new generations cannot reference it. The file's metadata remains retrievable with state=deleted.
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> Luma file ID to soft-delete.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Edit Image
>
> **Slug:** `LUMA_LABS_EDIT_IMAGE`
>
> Submit a paid, asynchronous Luma image-edit job. Returns immediately; use GET\_GENERATION with generation\_id to monitor it.
>
> #### Input Parameters
>
> **model** `string ("uni-1" | "uni-1-max")`
>
> Image model. uni-1-max produces higher-quality output at a higher price.
>
> **style** `string ("auto" | "manga")`
>
> Image style preset.
>
> **prompt** `string` *required*
>
> Instructions for editing the source image.
>
> **source** `object` *required*
>
> Image to edit.
>
> **user\_id** `string`
>
> Opaque, non-PII end-user identifier for usage and abuse attribution.
>
> **image\_ref** `array`
>
> Additional reference images for style or content guidance; up to 8.
>
> **web\_search** `boolean`
>
> Allow web search for grounding and reference images.
>
> **output\_format** `string ("png" | "jpeg")`
>
> Requested image output format.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Edit Video
>
> **Slug:** `LUMA_LABS_EDIT_VIDEO`
>
> Submit a paid, asynchronous Ray 3.2 video-edit job. Returns immediately; use GET\_GENERATION with generation\_id to monitor it.
>
> #### Input Parameters
>
> **video** `object`
>
> Ray 3.2 video-edit options.
>
> **prompt** `string` *required*
>
> Instructions for editing the source video.
>
> **source** `object` *required*
>
> Video to edit; URL/data sources require video/\* media\_type.
>
> **user\_id** `string`
>
> Opaque, non-PII end-user identifier for usage and abuse attribution.
>
> **web\_search** `boolean`
>
> Allow web search for grounding and reference images.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Extract Image Layers
>
> **Slug:** `LUMA_LABS_EXTRACT_IMAGE_LAYERS`
>
> Submit a paid, asynchronous Luma image layer-extraction job. Pricing is flat per generation at the selected resolution, regardless of layer count; use GET\_GENERATION with generation\_id to monitor the job.
>
> #### Input Parameters
>
> **prompt** `string` *required*
>
> Optional instructions for decomposing the source image into layers; pass an empty string for automatic decomposition.
>
> **source** `object` *required*
>
> Image to decompose into layers.
>
> **user\_id** `string`
>
> Opaque, non-PII end-user identifier for usage and abuse attribution.
>
> **layering** `object`
>
> Layer extraction output options.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Generate Image
>
> **Slug:** `LUMA_LABS_GENERATE_IMAGE`
>
> Submit a paid, asynchronous Luma image generation job. Returns immediately; use GET\_GENERATION with generation\_id to monitor it. Managed Instant calls must specify model explicitly. Maximum estimated Instant cost: \$3.00 per call.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.04 per image (uni-1) or \$0.1 (uni-1-max); +\$0.003 per reference image.
>
> #### Input Parameters
>
> **model** `string ("uni-1" | "uni-1-max")`
>
> Image model. uni-1-max produces higher-quality output at a higher price.
>
> **style** `string ("auto" | "manga")`
>
> Image style preset.
>
> **prompt** `string` *required*
>
> Image generation instructions.
>
> **user\_id** `string`
>
> Opaque, non-PII end-user identifier for usage and abuse attribution.
>
> **image\_ref** `array`
>
> Reference images for style or content guidance; up to 9.
>
> **web\_search** `boolean`
>
> Allow web search for grounding and reference images.
>
> **aspect\_ratio** `string ("3:1" | "2:1" | "16:9" | "3:2" | "1:1" | "2:3" | "9:16" | "1:2" | "1:3")`
>
> Requested output aspect ratio.
>
> **output\_format** `string ("png" | "jpeg")`
>
> Requested image output format.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Generate Video
>
> **Slug:** `LUMA_LABS_GENERATE_VIDEO`
>
> Submit a paid, asynchronous Ray 3.2 video generation job. Returns immediately; use GET\_GENERATION with generation\_id to monitor it. Managed Instant calls must specify video.resolution, video.duration, video.hdr, and video.exr\_export. Maximum estimated Instant cost: \$3.00 per call.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** From \$0.06 per 5-second 360p video; varies with resolution and duration.
>
> #### Input Parameters
>
> **video** `object`
>
> Ray 3.2 video generation options.
>
> **prompt** `string` *required*
>
> Video generation instructions.
>
> **user\_id** `string`
>
> Opaque, non-PII end-user identifier for usage and abuse attribution.
>
> **web\_search** `boolean`
>
> Allow web search for grounding and reference images.
>
> **aspect\_ratio** `string ("9:16" | "3:4" | "1:1" | "4:3" | "16:9" | "21:9")`
>
> Requested output aspect ratio.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get File
>
> **Slug:** `LUMA_LABS_GET_FILE`
>
> Get a Luma file's metadata and current ingest, moderation, or deletion state. Soft-deleted files remain retrievable with state=deleted.
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> Luma file ID returned by UPLOAD\_FILE or LIST\_FILES.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Generation
>
> **Slug:** `LUMA_LABS_GET_GENERATION`
>
> Get the current state, failure details, and output URLs for a Luma generation.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0 per request
>
> #### Input Parameters
>
> **generation\_id** `string` *required*
>
> Generation ID returned by a Luma image, video, edit, reframe, or layer-extraction tool.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Files
>
> **Slug:** `LUMA_LABS_LIST_FILES`
>
> List files in the connected Luma account, newest first, with optional state and purpose filters. Returns one page and a cursor for continuation.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum files to return in this page (1-100).
>
> **state** `string ("pending" | "ready" | "failed" | "deleted")`
>
> Return only files in this ingest or deletion state.
>
> **cursor** `string`
>
> Opaque next\_cursor from a previous LIST\_FILES response.
>
> **purpose** `string ("input" | "reference")`
>
> Return only files with this purpose.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Reframe Video
>
> **Slug:** `LUMA_LABS_REFRAME_VIDEO`
>
> Submit a paid, asynchronous Ray 3.2 video-reframe job. Returns immediately; use GET\_GENERATION with generation\_id to monitor it.
>
> #### Input Parameters
>
> **video** `object`
>
> Ray 3.2 video-reframe options.
>
> **prompt** `string` *required*
>
> Instructions for reframing the source video.
>
> **source** `object` *required*
>
> Video to reframe; URL/data sources require video/\* media\_type.
>
> **user\_id** `string`
>
> Opaque, non-PII end-user identifier for usage and abuse attribution.
>
> **web\_search** `boolean`
>
> Allow web search for grounding and reference images.
>
> **aspect\_ratio** `string ("9:16" | "3:4" | "1:1" | "4:3" | "16:9" | "21:9")` *required*
>
> Required output aspect ratio.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upload File
>
> **Slug:** `LUMA_LABS_UPLOAD_FILE`
>
> Directly upload file bytes to Luma and return the file ID, metadata, and current upload/ingest state.
>
> #### Input Parameters
>
> **file** `object` *required*
>
> File whose bytes will be uploaded to Luma.
>
> **purpose** `string ("input" | "reference")`
>
> How the file will be used: input for primary source material or reference for style and content guidance.
>
> **user\_id** `string`
>
> Optional opaque, non-PII end-user identifier for abuse attribution.
>
> **expires\_at** `string`
>
> Optional ISO 8601 time after which Luma may delete the file.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
