Text to image in about two seconds with eight-step distilled model
Free AI image generation platform with lightning-fast creation
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Free credits available; paid annual plans with 50% launch discount: Basic $9.9/month (800 credits/month, 9600 credits/year), Professional $19.9/month (2000 credits/month, 24000 credits/year), Enterprise $44.9/month (6000 credits/month, 72000 credits/year). Monthly plans also available. Per-render co
Free: 10 credits per day. Premium: $7/month (2,000 credits per month) or $2.45 per 1,000 credits annually. Elite: $12/month (5,000 credits per month) or $1.98 per 1,000 credits annually. Video Pro: $50/month (25,000 credits per month for video generation). Pay as you go also available at $3.50 per 1
Key features
Eight-step sampling produces 1024px drafts in roughly two seconds
Text to image and image to image workflows in one workspace
Support for LoRA attachments with no extra render cost
Resolution from small exploratory sizes up to 2K
Open weights published under custom licence permitting commercial use
Photographic base behaviour from 12B model trained from scratch
LoRAs behave as bipolar sliders for intensity control mid-series
Browser-based workspace with no GPU or local install required
Same 12B backbone as standard Krea 2 via trajectory distillation
Unlimited exports in PNG, JPG and WebP formats
AI Image Generation from text prompts
4K print-quality output
Bilingual prompt support in English and Chinese
Image editing with natural language
Prompt extraction from images
Creative Engine for prompt expansion
Multiple AI models including GPT Image 2 and Qwen Image 3
Video generation with AI
Hundreds of artistic styles
2-5 second generation speed
What makes it different
Two-second generation speed enables iteration-heavy workflows instead of single-frame rendering
Open weights allow running the same model locally without vendor lock-in
Trajectory distillation preserves detail of full 12B model at eight-step speed
Lightweight 6B parameter model optimized for fast generation
37% better Chinese language accuracy than alternatives
DiT architecture optimization for flagship quality
Open-source model that can run locally
Actually free with transparent pricing and clear safety rules