GET
/v1/schemas/fal/image/blackforestlabs/flux-3/text-to-image
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source tracea336d9338e520fe94b2edb0507e023b6022d079d69ca55b085969c2f6892c3e3{
"fetchedAt": 1792731610,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
8 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | The prompt to generate an image from. | |
| version | const | The model version. | "latest" · default: "latest" |
| safety_tolerance | integer | Safety tolerance, from 0 (strictest) to 4. | 0 ≤ n ≤ 4 · default: 2 |
| resolution | enum | Output resolution tier. 4k can take several minutes. | 768sq | 1k | 1.5k | 2k | 4k · default: "1k" |
| sync_mode | boolean | Return the image as a data URI instead of storing it in request history. | default: false |
| aspect_ratio | enum | Output aspect ratio. Auto uses the first reference image when editing. | auto | 21:9 | 2:1 | 16:9 | 3:2 | 7:5 · +9 more · default: "auto" |
| enable_prompt_expansion | boolean | Expand the prompt while preserving its intent and reference roles. | default: false |
| output_format | enum | The format of the generated image. | jpeg | png · default: "jpeg" |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"blackforestlabs/flux-3/text-to-image","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}