HunyuanOCR
A versatile, all-in-one OCR model
A versatile, all-in-one OCR model
Generate videos from images and prompts
Generate speech from text using Microsoft Edge TTS
Remove background from images
Chat with an AI assistant using text and images
Qwen Image Editing Fusion Collection LoRA Demo
Track, rank and evaluate open LLMs and chatbots
νκ΅μ΄ TTS λͺ¨λΈμ λΈλΌμΈλ ν μ€νΈλ‘ λΉκ΅ νκ°νμΈμ!
Learn about ML and Transformers through nanochat
Generate high-quality images from text prompts
Qwen-Image-2509-CharacterSheet
Generate edited images with masks and prompts
Create your own AI comic with a single prompt
Upgraded to v1.0!
Text-to-3D and Image-to-3D Generation
Kontext image editing on FLUX[dev]
Generate web application code from descriptions
Nova Furry XL | Illustrious v7 to v13.5
Generate videos from start and end images with prompts
Read a tutorial on robot learning
Transform video style with text prompts
Let your character interact naturally
Display and request speech recognition model benchmarks
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)