Swap characters, outfits, objects or locations in video while preserving motion and camera movement
Open-source SDXL-based AI model for native high-resolution anime art generation
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 for personal and research use; prohibits closed-source proprietary monetization
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
Native 1536x1536 high-resolution generation without upscaling
Hybrid Prompting System combining natural English and Danbooru tags
Stable text encoder fine-tuning for superior concept understanding
Trained on comprehensive Danbooru2023 dataset
Full compatibility with ComfyUI, Automatic1111, Forge, and Draw Things
Superior anatomy rendering with flawless hands and character details
V-Prediction architecture for enhanced dynamic range and contrast
Highly flexible base canvas for LoRA training and custom checkpoints
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
Only open-source SDXL model natively trained at 1536x1536 resolution
Stylistically neutral untuned base canvas unlike Pony Diffusion
Continuous rapid iterations from v0.1 to v3.5 with aggressive optimization
Thousands of compatible community-trained LoRAs and derivatives
Genjutsu AI
Illustrious XL