GET
/v1/schemas/fal/image/fal-ai/ccsr
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above.Source tracea51a028ff6d9422ffeb627c4c120d20243490089151156d654288346eebcbcb7{
"fetchedAt": 1783329487,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
13 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| image_url* | string | The URL or data URI of the image to upscale. | |
| tile_diffusion | enum | If specified, a patch-based sampling strategy will be used for sampling. | none | mix | gaussian · default: "none" |
| seed | integer | Seed for reproducibility. Different seeds will make slightly different results. | nullable |
| tile_diffusion_stride | integer | Stride of sliding patch. | 128 ≤ n ≤ 1024 · default: 512 |
| t_min | number | The starting point of uniform sampling strategy. | 0 ≤ n ≤ 1 · default: 0.3333 |
| tile_vae_encoder_size | integer | Size of latent image | 128 ≤ n ≤ 2048 · default: 1024 |
| scale | number | The scale of the output image. The higher the scale, the bigger the output image will be. | 1 ≤ n ≤ 4 · default: 2 |
| color_fix_type | enum | Type of color correction for samples. | none | wavelet | adain · default: "adain" |
| tile_diffusion_size | integer | Size of patch. | 256 ≤ n ≤ 2048 · default: 1024 |
| steps | integer | The number of steps to run the model for. The higher the number the better the quality and longer it will take to generate. | 10 ≤ n ≤ 100 · default: 50 |
| t_max | number | The ending point of uniform sampling strategy. | 0 ≤ n ≤ 1 · default: 0.6667 |
| tile_vae | boolean | If specified, a patch-based sampling strategy will be used for VAE decoding. | default: false |
| tile_vae_decoder_size | integer | Size of VAE patch. | 64 ≤ n ≤ 2048 · default: 226 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/ccsr","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}