GET

/v1/schemas/fal/image/fal-ai/ernie-image/lora

Accept:

kind inputactivity imagehash 4c973124…extracted Nov 13, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `f775b3e5f0da73ec589cba00e4a063c5b4959e0d1b1e09e1708468396ea87644` { "fetchedAt": 1794546001, "extractorVersion": "2", "verifiedAt": null }

Request body

13 properties · 1 required · 2 $defs

property	type	description	constraints
prompt*	string	Text prompt for image generation. Supports English, Chinese, and Japanese.
output_format	enum	Output image format.	jpeg \| png · default: "jpeg"
enable_prompt_expansion	boolean	If True, the prompt will be enhanced using an LLM for more detailed results.	default: true
guidance_scale	number	Classifier-free guidance scale.	1 ≤ n ≤ 20 · default: 5
sync_mode	boolean	If True, the image will be returned as a data URI instead of a URL.	default: false
num_inference_steps	integer	Number of denoising steps.	1 ≤ n ≤ 100 · default: 50
loras	LoraWeight[]	The LoRAs to use for image generation. You can use up to 3 LoRAs and they will be merged together to generate the final image.	items ≤ 3 · default: []
image_size	ImageSize \| enum	The size of the generated image.	default: "square_hd"
num_images	integer	Number of images to generate.	1 ≤ n ≤ 4 · default: 1
seed	integer	Random seed for reproducibility.	nullable
acceleration	enum	The acceleration level to use for the image generation.	none \| regular \| high · default: "regular"
negative_prompt	string	Negative prompt to guide what should not be in the image.	default: ""
enable_safety_checker	boolean	Enable NSFW safety checking on the generated images. Disabling it requires account authorization; unauthorized requests are always checked.	default: true

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

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
path*	string	URL or the path to the LoRA weights.

Validate a payload

before you spend tokens

shell

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