Free online AI face swap tool for photos, videos and GIFs
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
Freemium
Open source
Pricing
Free: 30 credits per week. One-time payments: 600 credits for $9.99 (60 credits per dollar, 25% off from $12.99), 1400 credits for $19.99 (70 credits per dollar, 35% off from $29.99), 4000 credits for $49.99 (80 credits per dollar, 45% off from $89.99), 8500 credits for $99.99 (85 credits per dollar
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
Swap faces in photos, videos, and GIFs
Multiple face swaps in one video
No watermarks on results
No software download required
Gender-bending transformations
Swap faces with celebrities
Support for MP4, MOV, GIF, WEBM formats
Three model quality options: Basic, HD, Pro
Batch face swap processing
Artistic face blending into paintings
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
Completely free to try with no watermarks on results
Fast processing of face swaps in seconds
Realistic AI output with natural expressions and details
Works entirely online in browser without downloads
Lower cost compared to competitors at $0.01 per second or per picture
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