Text to image in about two seconds with eight-step distilled model
Turn ideas into music with AI
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 plan with 3 AI music credits; Basic at $14.9/month (200 credits); Standard at $29.9/month (600 credits); Professional at $129.8/month (Unlimited credits). Yearly subscriptions save 40%. All plans include commercial licensing.
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 Song Generator - create complete songs from lyrics or text prompts
AI Instrumental Generator - create music without lead vocals
AI Music Video Generator - pair music with visual content
AI Voice Cover Generator - effortlessly audition different voices on songs
AI Stem Splitter - separate audio into vocal and instrumental elements
AI Lyrics Generator - develop lyric ideas from genre, mood, or topic
AI MIDI Generator - craft melodies, chords, and rhythms with built-in sequencer
Music Mastering - apply intelligent mastering to automatically balance mix
Generate music up to 8 minutes long
100% royalty-free with commercial licensing
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
All-in-one platform combining song generation with supporting music tools in one place
No production software or musical training required
Trained with 300 million+ data samples
Multiple generation modes for different creative needs
Krea 2 Turbo