GET

/v1/schemas/fal/image/openai/gpt-image-2.6/flare/edit

Accept:

kind inputactivity imagehash 031f5370…extracted Nov 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `a8ffc6ef962ea4593a3d341e5b93aad6bef5f3c4078bcbe7fec8be66b57acd22` { "fetchedAt": 1793941202, "extractorVersion": "1", "verifiedAt": null }

Request body

15 properties · 2 required · 1 $defs

property	type	description	constraints
prompt*	string	The prompt for image generation	length ≥ 1 · length ≤ 32000
image_urls*	string[]	The URLs of the images to use as a reference for the generation. A maximum of 16 images are allowed.	items ≤ 16
output_compression	integer	Compression level from 0 to 100. Only supported when output_format is 'jpeg' or 'webp'.	0 ≤ n ≤ 100 · nullable
frame_count	integer	GIF only: number of frames. image_size applies to each frame; reduce size or count if the request exceeds the pixel budget.	2 ≤ n ≤ 16 · default: 9
reasoning_effort	enum	How much the model plans before rendering, independently of quality (OpenAI `complexity`). Higher levels can help with dense text and complex layouts but add latency.	low \| medium \| high · default: "high"
mask_url	string	Mask image URL. White marks regions to edit and black marks regions to keep.	nullable
output_format	enum	Output format for the images. 'gif' returns an animation.	jpeg \| png \| webp \| gif · default: "png"
background	enum	Background for the generated image	auto \| transparent \| opaque · default: "auto"
markup_image_url	string	Transparent PNG containing only annotations (circles, arrows, notes) that guide the edit of the first image. Must match the first image's dimensions. Cannot be combined with mask_url. Reference images are sent unmodified when set.	nullable
sync_mode	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	default: false
num_images	integer	Number of images to generate. Must be 1 for SVG output. For GIF output, all frames of all outputs share the request's pixel budget.	1 ≤ n ≤ 10 · default: 1
quality	enum	Rendering quality for the generated image. For SVG output it controls the reference image used to create the vector.	auto \| low \| medium \| high \| xhigh \| max · default: "high"
frame_duration_ms	integer	GIF only: milliseconds per frame, rounded to 10 ms.	20 ≤ n ≤ 2000 · default: 200
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
image_size	ImageSize \| enum	The size of the generated image. Use 'auto' to infer from input images.	default: "auto"

Types

1 $defs

ImageSizeobject

width	integer	The width of the generated image.	0 < n ≤ 14142 · default: 512
height	integer	The height of the generated image.	0 < n ≤ 14142 · default: 512

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"openai/gpt-image-2.6/flare/edit","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}