AI talking-head video editor for creators who film themselves
Text to image in about two seconds with eight-step distilled model
Stage
Startup
Not given
Founded
Not given
Not given
Based in
GE
Not given
Pricing model
Paid
Freemium
Pricing
Starter: $19/month or $149/year for 15 videos per month. Creator: $29/month or $199/year for 30 videos per month. Pro: $69/month or $499/year for 100 videos per month. Single videos: $5 each.
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
Key features
Automatic take selection and false start removal
Captions and title card added
Watermarked preview before payment
Plain English revision requests
Up to 2 revisions before payment, 10 after
Browser-based, no installation required
9:16 vertical format ready to post
Customizable caption font and color
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
What makes it different
No timeline editing required; communicate changes in plain English
Watch finished video with watermark before paying
Built specifically for raw vertical phone recordings with retakes and false starts
One-click vertical format optimized for social platforms
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