Open-source SDXL-based AI model for native high-resolution anime art generation
Free AI face swap online - swap a face into any photo in seconds
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Open source
Free
Pricing
Free for personal and research use; prohibits closed-source proprietary monetization
Completely free. Users start with 500 free credits, earn +100 credits daily by logging in, and +100 credits for each friend referred. A small watermark can be removed by referring 10 friends for 1 month watermark-free access or 100 friends for 1 year.
Key features
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
Face swap in photos with advanced face detection and blending
GIF and video face swapping with frame tracking
Image upscaling and enhancement
Photo restoration and background removal
AI image generation from text prompts
Automatic upload deletion and no public gallery
Supports JPG, PNG and WebP formats up to 15 MB
Group face swapping for multiple faces
Consent-required workflow with confirmation step
AI clothes changing tool
What makes it different
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
Completely free with no signup, card, or account required
Privacy-first design with automatic upload deletion and no data training
Advanced AI blending that matches skin tone, lighting and edges for realistic results