Bria FIBO 1.5 Image

This family comes from Bria and keeps the text variant to a single resolution setting, so the only decision about the output is its shape, picked from a fixed list that runs from square out to wide and tall frames. Every shape costs the same, so choose the proportion the picture will actually be used at. What you type goes in as you typed it: there is no prompt rewriter in between, so say plainly what the frame should hold. Both variants take a seed, so when a draw is worth coming back to, note it along with the wording.

• Size: 2048×2048 (1:1)2304×1536 (3:2)1536×2304 (2:3)2048×1536 (4:3)1536×2048 (3:4)2048×1152 (16:9)1152×2048 (9:16)

How the image side of the catalog works as a whole, and what it allows, is on the uncensored AI image generator page; changing a picture you already have is covered by the uncensored image editor.

Send vellria-bria-fibo-1-5-image as the model field to POST /v1/generate/image, with your API key as a Bearer token. The request below uses this model's default settings from the catalog and returns a generation id to poll.

curl https://vellria.com/v1/generate/image \
  -H "Authorization: Bearer vll_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vellria-bria-fibo-1-5-image",
    "prompt": "…",
    "size": "2048*2048"
  }'

Every parameter, the polling call and the upload endpoint are in the API documentation; what the image endpoints allow is on the NSFW image API page.