Self Forcing Wan 2.1
Real-time video generation
Real-time video generation
nanonets ocr / typhoon ocr / smoldocling / monkey ocr
OmniGen2: Unified Image Understanding and Generation.
Display winners and videos from a hackathon
Chat with Kimi-Dev to debug code
Generate a modified image based on a reference and prompt
VideoRefer x VideoLLaMA3
Generate custom songs from lyrics
Next-Gen High-Resolution 3D Model Generation
Generate any application with DeepSeek
Image-to-3D Generation
Generate code from text prompts
Part-level image-to-3D generation.
Generate a video animation from an image
Generate custom songs from lyrics
Real-time video generation
Free Text-To-Speech generator with Emotion control (OpenAI)
OmniGen2: Unified Image Understanding and Generation.
Generate images from text prompts
Upload images to see virtual garment try-on
NotebookLM conversational speech model
Expressive Zeroshot TTS
Create datasets using AI and web search
Versatile Single-Image 3D Face Reconstruction
nanonets ocr / typhoon ocr / smoldocling / monkey ocr
Flexible Photo Recrafting While Preserving Your Identity
ultra-fast video model, LTX 0.9.7 13B distilled
Create your own AI comic with a single prompt
MidJour | A RealVisXL_Turbo | IRL HI-Res Images Gen
Embedding Leaderboard
Browse apps made with DeepSite
VGGT (CVPR 2025)