Appearance

PATINA

POST/v1/run

Material Extract by patina - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to patina/material/extract.

Default: patina/material/extract

stringpromptrequired

Describe which texture to extract from the image.

stringimagerequired

URL of the image to extract a texture from.

Optional<integer>num_inference_steps

Number of denoising steps for texture generation.

Range: 1 to 8

Default: 8

Optional<number>strength

How much to transform the input image. Only used when image_url is provided.

Range: −∞ to 1

Default: 0.6

Optional<string>output_format

Output image format for textures and PBR maps.

Allowed values: jpeg, png

Default: png

Optional<array<string>>maps

Which PBR maps to predict. Deselect all to skip PBR estimation entirely. Defaults to all five.

Default: basecolor,normal,roughness,metalness,height

Optional<integer>tile_size

Tile size in latent space (64 = 512px, 128 = 1024px).

Range: 32 to 256

Default: 128

Optional<integer>upscale_factor

Upscale factor for predicted PBR maps via SeedVR seamless upscaling. 0 = no upscaling, 2 = 2× resolution, 4 = 4× resolution. The base texture image is not upscaled.

Allowed values: 0, 2, 4

Default: 0

Optional<string>tiling_mode

Tiling direction: 'both' (omnidirectional), 'horizontal', or 'vertical'.

Allowed values: both, horizontal, vertical

Default: both

Optional<integer>tile_stride

Tile stride in latent space.

Range: 16 to 128

Default: 64

Optional<string>aspect_ratio

The aspect ratio of the generated image.

Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16

Optional<integer>seed

Random seed for reproducible generation.

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-to-image

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async