AI photo editor for restaurant menu photos using text prompts
Generative video models for animation
Stage
Startup
Not given
Founded
2025
Not given
Based in
US
US
Pricing model
Freemium
Not given
Pricing
Monthly Plan: $19/month with 300 photo edits per month. Annual Plan: $159/year (billed yearly, $13.25/month) with 300 photo edits per month. Both plans include text editing, version history, gallery storage, batch processing up to 10 photos, free hosted web menu, and priority support. Annual plan in
Not given
Key features
Text prompt editing - type any change like add ingredients, adjust lighting, or swap backgrounds
Full version history - every edit saved, jump back to any previous version
Batch processing - process up to 10 photos at once with consistent edits
Automatic gallery storage - all processed images organized by date with search functionality
Multi-platform export - sized for DoorDash, Uber Eats, Grubhub, Instagram
Free hosted web menu with QR code for each restaurant
Grid editing - divide image into sections and edit specific areas independently
Ingredient swapping - change proteins, sides, sauces and other ingredients in photos
Pyramid-JiT (P-JiT) architecture with 32×32 token reduction
4× more aggressive token reduction than Linum v2
Converges in 11× fewer samples than Linum v2
2B-parameter model with frozen Qwen text encoder
Pixel-space diffusion with multi-resolution readouts
PixelREPA alignment with DINOv3-L
Curriculum learning over noise schedule
What makes it different
Edits real photos, not AI-generated food - preserves original dish while making requested changes
Results in about 15 seconds - dramatically faster than hiring a photographer
Works with smartphone photos - no professional equipment or studio setup required
Built specifically for restaurants - understands food and delivers consistent results
Low-cost training: full 2B model trained for just $21K in compute
Controls baked into model training rather than post-hoc fine-tuning
Pixel-space compression without separate VAE bottleneck
Apache 2.0 open release with full model weights and code
MenuCapture
Linum