Vellria V1 Image

The Vellria line's image model keeps every run at one resolution tier and one price, so the choices that remain are the wording and the frame. The shape comes from a short fixed list running from square to wide and tall, and since none of them costs more than another, pick the proportion the picture will actually be shown at. There is no seed to note, so when a draw is worth keeping, save the picture itself rather than hoping to land on it again.

• Size: 2048×2048 (1:1, 2K)2364×1773 (4:3, 2K)1773×2364 (3:4, 2K)2730×1536 (16:9, 2K)1536×2730 (9:16, 2K)

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-v1-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-v1-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.