GET

/v1/schemas/fal/image/fal-ai%2Fernie-image%2Flora%2Fturbo

kind inputactivity imagehash 00b5f503…extracted Nov 13, 2026version currentsource upstream spec ↗

Request body

13 properties · 1 required · 2 $defs
propertytypedescriptionconstraints
prompt*stringText prompt for image generation. Supports English, Chinese, and Japanese.
output_formatenumOutput image format.jpeg | png · default: "jpeg"
enable_prompt_expansionbooleanIf True, the prompt will be enhanced using an LLM for more detailed results.default: true
guidance_scalenumberClassifier-free guidance scale.1 ≤ n ≤ 20 · default: 1
sync_modebooleanIf True, the image will be returned as a data URI instead of a URL.default: false
num_inference_stepsintegerNumber of denoising steps. Turbo model is optimized for 8 steps.1 ≤ n ≤ 20 · default: 8
lorasLoraWeight[]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_sizeImageSize | enumThe size of the generated image.default: "square_hd"
num_imagesintegerNumber of images to generate.1 ≤ n ≤ 4 · default: 1
seedintegerRandom seed for reproducibility.nullable
accelerationenumThe acceleration level to use for the image generation.none | regular | high · default: "regular"
negative_promptstringNegative prompt to guide what should not be in the image.default: ""
enable_safety_checkerbooleanEnable NSFW safety checking on the generated images. Disabling it requires account authorization; unauthorized requests are always checked.default: true

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/turbo","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}