Text to image
Vellria Flash
The fastest and cheapest image model. For drafts, variations and quick tests.
1 credit
Catalog
Models
20 models
Text to image
Seedream 5 Pro Uncensored
The flagship image model, focused on detail and composition. 2K output only.
9 credits
Image to image
Seedream 5 Pro Uncensored Edit
The flagship editing model. Takes up to ten references and preserves identity and lighting.
9 credits
Text to image
Qwen 3 Pro Uncensored
Strong on long, complex prompts; stays faithful to scene composition and text.
6 credits
Image to image
Qwen 3 Pro Uncensored Edit
Edits using the images you provide as references, preserving character and scene.
6 credits
Text to image
Seedream 5 Lite Uncensored
Fast, cheap Seedream. Reaches 4K and is good at typography and poster work.
4 credits
Image to image
Seedream 5 Lite Uncensored Edit
Takes up to fourteen references and redraws the images you provide.
4 credits
Text to video
Seedance 2.5
A cinematic video model. Long scenes and natural camera movement.
from 14 credits / s
Text to video
MiniMax H3 Uncensored
Fast, economical video generation. Straight from text to scene.
6 credits / s
Image to video
MiniMax H3 Uncensored Image
Takes the image you provide as the first frame and animates it.
6 credits / s
Reference to video
MiniMax H3 Uncensored Reference
Generates video that keeps character consistency across several references.
6 credits / s
Text to video
HappyHorse 1.1 Uncensored
A video model that reaches 1080p. Nine aspect ratios, 3–15 seconds.
from 7 credits / s
Image to video
HappyHorse 1.1 Uncensored Image
Takes your image as the first frame and animates it up to 1080p.
from 7 credits / s
Reference to video
HappyHorse 1.1 Uncensored Reference
Takes up to nine references and generates video that preserves subject and scene.
from 7 credits / s
Text to video
Wan 3.0 Uncensored
The cheapest video in the catalog. A single scene up to 30 seconds, with audio.
from 5 credits / s
Image to video
Wan 3.0 Uncensored Image
Takes your image as the first frame and animates it for up to 30 seconds.
from 5 credits / s
Reference to video
Wan 3.0 Uncensored Reference
Takes up to ten references and generates video that preserves character and place.
from 5 credits / s
Text to video
Wan 3.0 Pro Uncensored
The large version of Wan 3.0. Higher detail and steadier motion.
from 7 credits / s
Image to video
Wan 3.0 Pro Uncensored Image
Starts from the first frame and continues with Pro's detail and motion quality.
from 7 credits / s
Reference to video
Wan 3.0 Pro Uncensored Reference
Combines ten references at Pro quality; identity and place are preserved.
from 7 credits / s