Music Flamingo
Upload audio or provide a YouTube URL to get detailed music insights
Upload audio or provide a YouTube URL to get detailed music insights
Track and label objects in videos using text prompts or clicks
Segment objects in images using text prompts
Process and analyze video content using keywords
Generate a storybook page with text, image, and audio
Self-Driving Backends that Think, Talk, and Execute
Improve and restore old photos with faces
Transcribe audio files or YouTube videos into text
Generate stunning high quality illusion artwork
Generate voice from text using a reference audio
In-browser WebGPU background removal
Create quantized models from Hugging Face repos
Generate detailed prompts from images for AI art generation
Generate depth maps from images
Easily expand image boundaries
Enhance prompts using structured templates
Scrape website content and generate sitemaps
Fast 8 step inference of Qwen Image Edit 2509
Official Demo of Lotus-2 (https://lotus-2.github.io/)
Parse and recognize text in images
Generate images in 8-steps
Medical MCP agentic RAG & Search with MedSwin
Demo of the Collection of Qwen Image Editing LoRAs
Public Alpha AI -- best stocks for today -- ;) Best stock