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)
Ray 3.2: frame-by-frame video control and continuity across cuts
Uni-1.1: brand intelligence with style and character references
Luma Skills: reusable creative workflows for consistent output
Modify Video: video-to-video editing
Reframe: outpaint images and reframe videos
Camera Motion Concepts: learnable camera controls
Automatic continuity across video cuts
Cinematic quality finishing
Agent-driven research and refinement across video, image, audio, text
Team members and admins management
Fast variant generation: ten directions before standup
API access for Ray 3.2 and Uni-1.1
Third-party model integration (Veo 3.1, Kling Omni, GPT Image 2)
Image generation with GPT Image 2, Nano Banana, Seedream
Audio generation: ElevenLabs TTS, SFX, music
