GET
/v1/schemas/stability/image/v2beta/stable-image/generate/sd3
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace1ea5455da5ce2efef103daa142cc44a3e70b4fb3cfcdfa0c9a6a6f46d93912ea{
"fetchedAt": 1789536057,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
11 properties · 1 required · 4 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | any | ||
| mode | enum | Controls whether this is a text-to-image or image-to-image generation, which affects which parameters are required: - **text-to-image** requires only the `prompt` parameter - **image-to-image** requires the `prompt`, `image`, and `strength` parameters | text-to-image | image-to-image · default: "text-to-image" |
| image | string | The image to use as the starting point for the generation. | format: binary |
| strength | number | Sometimes referred to as _denoising_, this parameter controls how much influence the `image` parameter has on the generated image. A value of 0 would yield an image that is identical to the input. A value of 1 would be as if you passed in no image at all. | 0 ≤ n ≤ 1 |
| aspect_ratio | enum | Controls the aspect ratio of the generated image. Defaults to 1:1. | 21:9 | 16:9 | 3:2 | 5:4 | 1:1 | 4:5 · +3 more · default: "1:1" |
| model | enum | The model to use for generation. | sd3.5-large | sd3.5-large-turbo | sd3.5-medium · default: "sd3.5-large" |
| seed | number | A specific value that is used to guide the 'randomness' of the generation. (Omit this parameter or pass `0` to use a random seed.) | 0 ≤ n ≤ 4294967294 · default: 0 |
| output_format | enum | Dictates the `content-type` of the generated image. | png | jpeg | webp · default: "png" |
| style_preset | enum | Guides the image model towards a particular style. | enhance | anime | photographic | digital-art | comic-book | fantasy-art · +11 more |
| negative_prompt | string | any | ||
| cfg_scale | number | How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt). The _Large_ and _Medium_ models use a default of `4`. The _Turbo_ and _Flash_ model uses a default of `1`. | 1 ≤ n ≤ 10 |
Types
4 $defsNegativePromptstring
A blurb of text describing what you **do not** wish to see in the output image. This is an advanced feature.
length ≤ 10000
Promptstring
What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.
length ≥ 1 · length ≤ 10000
Seednumber
A specific value that is used to guide the 'randomness' of the generation. (Omit this parameter or pass `0` to use a random seed.)
0 ≤ n ≤ 4294967294 · default: 0
StylePresetenum
Guides the image model towards a particular style.
enhance | anime | photographic | digital-art | comic-book | fantasy-art · +11 more
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"stability","endpointId":"v2beta/stable-image/generate/sd3","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}