Features
Pretrained diffusion models for image, video, and audio generation
Modular DiffusionPipeline API with mix-and-match components
Support for LoRA and other adapters
Memory optimizations: offloading and quantization
torch.compile for faster inference
Integration with Hugging Face Hub for model sharing and loading
Training tools and fine-tuning examples
Hardware filter for finding compatible models (new, June 30, 2026)
Service Accounts for Enterprise programmatic access (new, June 12, 2026)
Workflow identity federation for CI publishing without secrets (new, June 8, 2026)
Hugging Face Diffusion Models Course available
Base Models only filter on Hub (new, May 28, 2026)
Audio-to-video music visualization
Style transfer and artistic filters
Animation from static images
High-resolution video output up to 1080p
Mobile app for iOS and Android
Customizable aspect ratios
Quick export to social media
Watermark-free exports on Pro tier
