Seedream 5 Pro Uncensored
Generates from a prompt, or edits from up to 10 references, at 2K in five frame shapes.
vellria-seedream-5-proSeedream 5 Pro is developed by ByteDance. Vellria provides access to the model; it does not own it. All trademarks belong to their respective owners.
Output
No generation yetCover art
10 credits
Your request will cost 10 credits.
Overview
This is the family for an image that is the deliverable — a cover, a key frame, a portrait you will actually use — rather than a pass you intend to redo. It rewards prompts that specify: where the subject sits in the frame, what the light is doing, what the lens is like, instead of a stack of adjectives. Prompt-only generation and editing render from the same base and offer the same sizes, so adding a reference is not a change of look.
Prompt or reference
Send a prompt alone for a frame that does not exist yet. Add a picture when you want part of it reworked — wardrobe, background, the light — while everything else stays where it is. References here are not free: images past the first add to what the run costs, so send what the edit actually needs rather than everything you have.
Specifications
- Size: 1536×1536 (1:1, 2K)1776×1328 (4:3, 2K)1328×1776 (3:4, 2K)2048×1152 (16:9, 2K)1152×2048 (9:16, 2K)
- Reference images: 1–10 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
| Size | Credits |
|---|---|
| 1536×1536 (1:1, 2K) | 10 credits |
| 1776×1328 (4:3, 2K) | 10 credits |
| 1328×1776 (3:4, 2K) | 10 credits |
| 2048×1152 (16:9, 2K) | 10 credits |
| 1152×2048 (9:16, 2K) | 10 credits |
+1 credit per extra image
Call it from the API
Send vellria-seedream-5-pro 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-pro",
"prompt": "…",
"size": "1536*1536"
}'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.