Swap characters, outfits, objects or locations in video while preserving motion and camera movement
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
Paid
Open source
Pricing
Credit packs: Mini $4.99 (10 credits), Starter $9.90 (25 credits), Creator $19.00 (60 credits), Pro $39.00 (140 credits). Standard quality costs 1 credit per second, 2K costs 2 credits per second. Credits never expire. Monthly subscription also available with 15% annual savings.
Free and open source
Key features
Character Swap mode to transform performers into illustrated, cartoon or 3D characters from reference images
Swap Anything mode to replace objects, outfits, products or backgrounds while keeping the performer
Processes videos 4–15 seconds long from uploaded clips up to 2 minutes
Runs entirely in browser with no installation required
Preserves original motion, camera movement and timing in generated videos
Automatic refunds for failed renders
Standard 768P and 2K resolution options
Commercial use license included for all generated content
Optional audio reference via public MP3 or WAV file links
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
Preserves original motion and camera work while swapping visual elements
No rotoscoping, green screen or reshoot needed
Powered by MiniMax H3 reference-to-video model
Transparent per-second credit pricing with upfront cost display
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
Genjutsu AI
CyberRealistic XL