Remove unwanted objects from videos and images with AI tracking
High-fidelity photorealistic AI image generation with natural prompting
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Open source
Pricing
Free: 10 free credits per account, no sign-up required. Pay as you go: $3.00 for 30 credits, $0.10 per credit. Credits cost 1 per detection and 4 per second of video (minimum 20 per run). Custom plans available.
Free and open source
Key features
Frame-by-frame AI tracking of moving objects
Automatic background reconstruction
Natural language prompts and brush masking
Works with MP4, MOV, JPG and PNG files
Browser-based with no desktop app required
Preserves original audio during video processing
Real-time tracking visualization
Handles motion, turns and camera pans
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
What makes it different
Single prompt or brush mark tracks automatically through entire video
Works for both videos and images with the same tool
Processes in browser without downloading a desktop application
Frame-locked tracking through motion and camera movement
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
CyberRealistic XL