Text to image in about two seconds with eight-step distilled model
AI agent for content creators
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
US
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: 20 credits per day, no card required. Lite: $9/month with 1,000 credits per month. Starter: $19/month with 2,000 credits per month. Pro: $49/month with 6,000 credits per month. All prices in USD.
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
Video editing by natural language description
Automatic subtitle generation in multiple languages
Thumbnail creation from footage or text description
Audio transcription with word-level timing
Text-to-speech voiceover generation
Motion graphics and animated sequences
Document analysis and PDF processing
Live progress visibility
Video generation from text descriptions
Multi-platform access via web, iOS, and Android
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
Natural conversation interface instead of complex editing timelines
No watermarks on exported files
Privacy-first processing with no model training on user content