Integrate Prodia's `inference.flux-fast.dev-kontext.img2img.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.flux-fast.dev-kontext.img2img.v1",
"config": {
"prompt": "puppies in a cloud, 4k",
"width": 1024,
"height": 1024,
"steps": 30,
"guidance_scale": 2.5
}
}'Input
Reference image for Kontext.
Limits : Max 10 MB, 2048x2048. Min 512x512.
Input description of desired output.
Apply a visual theme to your output image.
Amount of computational iterations to run. More is typically higher quality.
A randomness initializer for image reproducability.
When using JPEG output, return a progressive JPEG.
Output
Elapsed0.00s