Skip to content
Vellria

Seedream 5 Lite Uncensored

Generates from a prompt, or edits from up to 14 references, at 3K or 4K in eight shapes.

ImageText to image · Image to imageByteDance8 credits
vellria-seedream-5-lite
Docs

Seedream 5 Lite is developed by ByteDance. Vellria provides access to the model; it does not own it. All trademarks belong to their respective owners.

Input

Form

0 / 10000

Reference

0–14 images. You can upload files or paste https URLs; the provider downloads the image from the URL.

Settings

Sign in to run

No generation yet

No generation yet

Output

No generation yet

Cover art

8 credits

Sign in to run

Your request will cost 8 credits.

Overview

The same model runs in both directions here: from a written prompt, or from pictures you already have. Both draw from the same list of sizes, which matters more than it sounds — pick the output shape once when you generate from a prompt and every later edit comes back at exactly that shape. Nothing is resized or re-cropped between passes, so a long chain of edits stays the same picture rather than a series of crops.

Prompt or reference

What you are holding decides it, not taste. With only a description, the model generates; attach a picture and it edits instead. For a series where the same subject has to hold across images, draft once from a prompt and keep every later pass on a reference, feeding the previous result back in as you go.

Specifications

  • Size: 3072×3072 (1:1, 3K)3456×2592 (4:3, 3K)2592×3456 (3:4, 3K)3744×2496 (3:2, 4K)2496×3744 (2:3, 4K)4096×2304 (16:9, 4K)2304×4096 (9:16, 4K)4704×2016 (21:9, 4K)
  • Reference images: 1–14 reference images

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.

Pricing

SizeCredits
3072×3072 (1:1, 3K)8 credits
3456×2592 (4:3, 3K)8 credits
2592×3456 (3:4, 3K)8 credits
3744×2496 (3:2, 4K)8 credits
2496×3744 (2:3, 4K)8 credits
4096×2304 (16:9, 4K)8 credits
2304×4096 (9:16, 4K)8 credits
4704×2016 (21:9, 4K)8 credits

Call it from the API

Send vellria-seedream-5-lite 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-seedream-5-lite",
    "prompt": "…",
    "size": "3072*3072"
  }'

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.