High-fidelity photorealistic AI image generation with natural prompting
Turn screen recordings into narrated product videos
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Open source
Free trial
Pricing
Free and open source
Free during early access. After early access ends, pricing will be based on credits charged per minute of finished video and per added language. Exact rates to be announced.
Key features
High-fidelity skin and eye rendering with fine pores and light reflections
Robust composition coherence for multi-subject scenes and action shots
Baked-in VAE with optimized color tuning
Simple natural language prompting without complex templates
Compatible with ComfyUI, Automatic1111, and Forge
Works with popular SDXL ControlNets and IP-Adapters
Thousands of compatible LoRAs available
Optimized CFG sensitivity for high quality at lower scales
Natural light scattering and structural accuracy
Experimental Catalyst branch for continuous model evolution
AI script rewriting and editing
AI voiceover with 16 languages
Automatic click zoom and sync
Step-by-step guides as page or PDF
SRT and VTT captions
Chrome recorder and Mac app
Workspace with SSO and roles
Share links with viewer analytics
Credit estimate before export
Backgrounds, music, and speed presets
What makes it different
Minimal prompting complexity with natural language descriptions instead of complex embeddings
Eliminates artificial AI textures and generic rendering artifacts
Open-source with commercial use permissions
Seamless integration into existing AI image generation workflows
Continuously refined through community feedback and experimental development
Real footage never generated, only script and voice rewritten