Text to image in about two seconds with eight-step distilled model
AI caption and subtitle generator that adds captions to videos in seconds with no watermark
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Not given
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: 30 minutes of captions per month, 1080p MP4 export up to 3 minutes, 8 caption styles, SRT/VTT/TXT downloads up to 30 minutes, free translation into 100+ languages. Pro: $6.99/month (limited-time price, normally $9.99) or $59/year, unlimited captions on videos up to 90 minutes, all 22 caption s
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
Automatic speech transcription in 100 languages with automatic language detection
SRT, VTT and TXT subtitle file downloads
Free translation into 100+ languages
Copy caption style from screenshot functionality
Bilingual captions showing two languages simultaneously on Pro
Video processing entirely in browser with audio-only server transmission for privacy
Word-level timing synchronization for precise caption timing
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
Fastest among 10 tested caption tools, 6.7× faster than CapCut and 4.7× faster than VEED
Highest accuracy with 5.7% word error rate in October 2026 accuracy test of 8 caption tools
Video stays entirely private with only audio sent for transcription