Integrate Prodia's `inference.hypir.upscale.v1` using https://docs.prodia.com/llms.txtAPI request
Image inputs are sent as multipart form-data alongside the JSON job. See docs.prodia.com.
curl -X POST https://inference.prodia.com/v2/job \
-H "Authorization: Bearer $PRODIA_TOKEN" \
-H "Content-Type: application/json" \
-H "Accept: image/jpeg" \
-d '{
"type": "inference.hypir.upscale.v1",
"config": {
"factor": 2,
"patch_size": 512,
"stride": 256,
"model_t": 200,
"coeff_t": 200
}
}'Input
The filename of the target image.
Upscale factor is how many times larger the upscaled image will be (e.g. 2x).
A description of your image.
Style preset applies a common style to your prompt.
Tiling patch size.
Tiling stride length.
Model input timestep.
Timestep used to calculate the conversion coefficients from noise to data.
Output
Elapsed0.00s