Hunyuan3D-2.1
Image-to-3D Generation
Image-to-3D Generation
Create images from text and optional images
All-in-one face swapping: single photo, video, multi-source,
Generate expressive speech from text with emotion control
TTS demo for T5Gemma-TTS model
Use natural language to solve fun physics simulation puzzles
Model Browser
Chatterbox TTS supporting 23 languages
Edit and guide image generation
The ultimate guide to training LLM on large GPU Clusters
Remove reflections from images
All about Reachy Mini, from building to getting started
Translate and Lipsync any video clips to English
Swap faces in images
Free Text-To-Speech generator with Emotion control (OpenAI)
Display benchmark evaluation data for LLMs
Generate images from text prompts
Frontier multimodal AI, running entirely in your browser.
Generate images from text descriptions
Uncensored General Intelligence Leaderboard
Explore the Eiffel Tower Llama experiment with open-source models
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Generate code with AI
Nano Banana for Hugging Face PRO users