Vellria V1 Quality Video

This is the Vellria line at its dearer setting, meant for the take you intend to keep rather than the one you are still working out. Every second costs more here than on the speed setting, and the two share their lengths and resolution steps exactly, so the working pattern is to find the prompt, the framing and the length there, then re-run it here. That re-run is a fresh draw, not an enlargement of the earlier clip. Sound comes with every clip in both settings, so the audio is part of the take you pay for, not something added later.

• Resolution: 480p768p
• Duration: 5–15s
• Aspect ratio: 16:99:164:33:43:22:31:1

How the video side of the catalog works as a whole, and what it allows, is on the uncensored AI video generator page; explicit clips have their own page on NSFW video generation, and starting from a still is covered under NSFW image to video.

Send vellria-v1-quality-video as the model field to POST /v1/generate/video, 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/video \
  -H "Authorization: Bearer vll_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vellria-v1-quality-video",
    "prompt": "…",
    "duration": 5,
    "resolution": "480p",
    "ratio": "16:9"
  }'

Every parameter, the polling call and the upload endpoint are in the API documentation; every video model id with its price is on the NSFW video API page.