csviverdeia/upernet-ade20k
UperNet ConvNeXt-Small fine-tuned em ADE20K. Semantic segmentation: foto → seg map RGB. Pre-processor para controlnet-seg-room.
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).
|
{
"type": "object",
"title": "Input",
"required": [
"image"
],
"properties": {
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 0,
"description": "Foto a ser segmentada (qualquer cena, melhor pra interiores)."
},
"output_size": {
"type": "integer",
"title": "Output Size",
"default": 512,
"maximum": 1024.0,
"minimum": 256.0,
"x-order": 1,
"description": "Tamanho da imagem de sa\u00edda (quadrada). 512 \u00e9 compat\u00edvel com SD 1.5."
},
"return_class_counts": {
"type": "boolean",
"title": "Return Class Counts",
"default": true,
"x-order": 2,
"description": "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.
{
"type": "object",
"title": "Output"
}