GET
/v1/schemas/fal/image/fal-ai%2Fernie-image%2Flora%2Fturbo
Accept:
Request body
13 properties · 1 required · 2 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | Text prompt for image generation. Supports English, Chinese, and Japanese. | |
| seed | integer | Random seed for reproducibility. | nullable |
| num_inference_steps | integer | Number of denoising steps. Turbo model is optimized for 8 steps. | 1 ≤ n ≤ 20 · default: 8 |
| enable_prompt_expansion | boolean | If True, the prompt will be enhanced using an LLM for more detailed results. | default: true |
| negative_prompt | string | Negative prompt to guide what should not be in the image. | default: "" |
| image_size | ImageSize | enum | The size of the generated image. | default: "square_hd" |
| acceleration | enum | The acceleration level to use for the image generation. | none | regular | high · default: "regular" |
| guidance_scale | number | Classifier-free guidance scale. | 1 ≤ n ≤ 20 · default: 1 |
| 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. | default: [] |
| output_format | enum | Output image format. | jpeg | png · default: "jpeg" |
| num_images | integer | Number of images to generate. | 1 ≤ n ≤ 4 · default: 1 |
| enable_safety_checker | boolean | Enable NSFW safety checking on the generated images. | default: true |
| sync_mode | boolean | If True, the image will be returned as a data URI instead of a URL. | default: false |
Validate a payload
before you spend tokensshell
$ 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", …}]}