csviverdeia/upernet-ade20k

UperNet ConvNeXt-Small fine-tuned em ADE20K. Semantic segmentation: foto → seg map RGB. Pre-processor para controlnet-seg-room.

Public
3 runs

Run csviverdeia/upernet-ade20k with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
image
string
Foto a ser segmentada (qualquer cena, melhor pra interiores).
output_size
integer
512

Min: 256.0

Max: 1024.0

Tamanho da imagem de saída (quadrada). 512 é compatível com SD 1.5.
return_class_counts
boolean
True
Retornar contagem de pixels por classe ADE20K (top classes encontradas).

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "object",
  "title": "Output"
}