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
Flexible Photo Recrafting While Preserving Your Identity
High-fidelity 3D Geometry Generation from images
Submit media inputs to generate text and speech responses
Generate 3D models from images
Scalable and Versatile 3D Generation from images
Convert images and text into scalable vector graphics (SVG) code
Large Animatable Human Model
Overlay garment on person image
Gemini 2.0 native image generation co-doodling
Execute custom commands
Generate images from text prompts
Reasoning + Multimodal + VLM + Deep Research + Agent
Deepseek v3-0324 + Real Time Deep Research
Text-to-3D and Image-to-3D Generation
Embedding Leaderboard
Generate app code from ideas
interactive demo for cube 3d model
Run specified code from environment variable
Try Orpheus TTS here
Generate virtual camera views from input images
Conversational speech generation
Hunyuan T1ๆจกๅไฝ้ช
Upload an image to find matching faces