SAM 3 is a foundation model for promptable segmentation
(Unofficial) Gradio demo for MiraTTS
High-fidelity 3D Generation from images
Enhance anime images and videos with super-resolution
View and manage multiple PDF files
Highlight and crop objects in images based on text prompts
Record and send live streams via Telegram
Generate natural-sounding speech from text
Create an interactive, emoji-filled video background with draggable text
Generate responses in a conversational chatbot