OctoTools
An Agentic Framework with Tools for Complex Reasoning
An Agentic Framework with Tools for Complex Reasoning
A leaderboard for LLMs powering smolagents
Conversational speech generation
Fast image relighting using Latent Bridge Matching
Image to Compositional 3D Scene Generation
Enhance image quality with real-time super-resolution
A demo for exploring and analyzing large-scale model repos
Generate edited images with prompts
Generate any application with DeepSeek
New Ghibli EasyControl model is now released!!
Generate 3D models from images
Flexible Photo Recrafting While Preserving Your Identity
High-fidelity 3D Geometry Generation from images
Scalable and Versatile 3D Generation from images
Overlay garment on person image
Execute custom commands
Submit media inputs to generate text and speech responses
Execute custom Python scripts from environment variables
Generate app code from ideas
Convert images and text into scalable vector graphics (SVG) code
Embedding Leaderboard
Text-to-3D and Image-to-3D Generation
Large Animatable Human Model
Gemini 2.0 native image generation co-doodling
Generate 3D texture from image
Generate images from text prompts
Trading Asset Sentiment Analysis
Generate polaroid-style images from text prompts
AI web app that transforms photos into Ghibli-style artwork
Create avatars and profile images, turning your memes
Generate animated portraits from images and audio
How Language Models Turn Text into Meaning, From Traditional