Lists (2)
Stars
A free, open source, and extensible speech-to-text application that works completely offline.
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.
🎨 Turn your roughest sketches into stunning 3D worlds by vibe drawing
Foundational Models for State-of-the-Art Speech and Text Translation
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Create images of a given character in different poses
Arbitrary-steps Image Super-resolution via Diffusion Inversion (CVPR 2025)
On-device Image Generation for Apple Silicon
Independent technology for modern publishing, memberships, subscriptions and newsletters.
Python tool for converting files and office documents to Markdown.
ComfyUI-OmniGen - A ComfyUI custom node implementation of OmniGen, a powerful text-to-image generation and editing model.
Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The …
The desktop app for ComfyUI (Windows & macOS)
[WACV 2025] Official implementation of "Face Anonymization Made Simple"
Awesome apps, software, and SaaS deals on Black Friday.
ML-powered speech recognition directly in your browser
A set of ComfyUI nodes for using models served by fal.ai and Replicate.com
Generate accurate transcripts using Apple's MLX framework
An extensive node suite for ComfyUI with over 210 new nodes
ControlNet++: All-in-one ControlNet for image generations and editing!