FLUX.1 Fill [dev]

from $0.0200 per job

Image
4.5s
inference.flux-fill.dev.v1
Integrate Prodia's `inference.flux-fill.dev.v1` using https://docs.prodia.com/llms.txt

API 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-fill.dev.v1",
  "config": {
    "prompt": "puppies in a cloud, 4k",
    "hyper": true,
    "guidance_scale": 28,
    "steps": 13,
    "max_sequence_length": 512,
    "width": 1024,
    "height": 1024
  }
}'

Input

Starting image to be edited.
Limits : Max 10 MB, 1920x1920. Min 256x256.

Black and white image where white is the area to be edited.
Limits : Max 10 MB, 1920x1920. Min 256x256.

Enable/disable Hyper LoRA

Output

Elapsed0.00s