GET

/v1/schemas/fal/image/fal-ai/qwen-image/image-to-image

Accept:

kind inputactivity imagehash e1e5d258…extracted Aug 8, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `ba6da9c86ff93464a507f11b5aaab9516363908cb22ce7dfd56d1ddf80929e5d` { "fetchedAt": 1786165357, "extractorVersion": "1", "verifiedAt": null }

Request body

15 properties · 2 required · 2 $defs

property	type	description	constraints
prompt*	string	The prompt to generate the image with
image_url*	string	The reference image to guide the generation.
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
loras	LoraWeight[]	The LoRAs to use for the image generation. You can use up to 3 LoRAs and they will be merged together to generate the final image.	default: []
use_turbo	boolean	Enable turbo mode for faster generation with high quality. When enabled, uses optimized settings (10 steps, CFG=1.2).	default: false
enable_safety_checker	boolean	If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.	default: true
guidance_scale	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.	0 ≤ n ≤ 20 · default: 2.5
image_size	ImageSize \| enum	The size of the generated image. By default, we will use the provided image for determining the image_size.	nullable
num_inference_steps	integer	The number of inference steps to perform.	2 ≤ n ≤ 250 · default: 30
seed	integer	The same seed and the same prompt given to the same version of the model will output the same image every time.	nullable
strength	number	Denoising strength. 1.0 = fully remake; 0.0 = preserve original.	0 ≤ n ≤ 1 · default: 0.6
negative_prompt	string	The negative prompt for the generation	default: " "
acceleration	enum	Acceleration level for image generation. Options: 'none', 'regular', 'high'. Higher acceleration increases speed. 'regular' balances speed and quality. 'high' is recommended for images without text.	none \| regular \| high · default: "none"
output_format	enum	The format of the generated image.	jpeg \| png · default: "png"
num_images	integer	The number of images to generate.	1 ≤ n ≤ 4 · default: 1

Types

2 $defs

ImageSizeobject

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

LoraWeightobject

path*	string	URL or the path to the LoRA weights.
scale	number	The scale of the LoRA weight. This is used to scale the LoRA weight before merging it with the base model.	0 ≤ n ≤ 4 · default: 1

Validate a payload

before you spend tokens

shell

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