Text to image in about two seconds with eight-step distilled model
Convert PowerPoint and PDF slides into narrated videos with an AI avatar presenter
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 tier: 60 credits on signup (enough for 6-page deck). Credits cost 10 per page. Credit packs: Starter $39 for 2,000 credits (~200 slides); Creator $99 for 6,000 credits (~600 slides); Studio $299 for 20,000 credits (~2,000 slides). All packs never expire. Credits can also be purchased via monthl
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
Cloud-based processing with no GPU installation required
Support for PowerPoint (.pptx, .ppt) and PDF files up to 40 pages
Editable draft scripts generated from slide text before rendering
Custom presenter registration from 8-30 seconds of video
Voice cloning from reference audio on all plans
Per-slide chapters for video navigation
Single MP4 output per deck with lip-sync
Failed renders fully refunded
Shareable links for finished videos without requiring viewer account
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
9–35× cheaper per minute than competitors like Synthesia and HeyGen
No video length cap: renders up to 80 minutes as a single video without splitting
Custom presenters and voice cloning included on all plans, including free tier
Self-hosted delivery option available for organizations with data residency requirements
Krea 2 Turbo
DocPresenter