XTTS
Generate realistic voice synthesis using text and reference audio
Generate realistic voice synthesis using text and reference audio
Generate videos by adding speech to images or videos
Generate captions for images in various styles
Executes geo-calculations without third-party APIs
Coding research assistant that generates code and tests it
Simple Interface to use LeRobot
Upscale images to higher resolutions
Video deep fake (uncensored)
Generate images from text prompts
A Step Towards Music Generation Foundation Model
NSFW FLUX Uncensored photo 'Text & Imagery for AI Limits'
RAG on documentations for your agent
core ocr / docscope vision / monkey ocr
TRELLIS is a large 3D asset generation model.
Demo of Normalized Attention Guidance for FLUX.1-dev
Upscale and enhance images with Real-ESRGAN
Generate personalized images with a face preservation
Uncensored General Intelligence Leaderboard
Restore and enhance images using text prompts
Wan2.1-T2V-14B + Fast 4-step with NAG + Automatic Audio
Generate images from text descriptions
Enhance and restore old photos with faces
Explore LLM performance across hardware
Transcribe audio and YouTube videos to text