Stars
The open creative studio on ComfyUI: images, video, 3D and audio on open weights, on your own GPU or the cloud. Camera motions, effects, apps, Cinema, Layers, Image to 3D and an AI agent.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent…
[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
A Claude Code skill for modeling real-world objects in Blender from reference images.
Open-source command-line interface for generating 3D models in Blender using AI.
Open Source Guitar Design for hobbyists and professional luthiers. CNC first designed, high customizable.
Token-efficient MCP adapter for Pi coding agent
Flipper Zero WiFi Marauder companion app
Flipper Zero companion app for GhostESP: Revival firmware
deepbeepmeep / WanGP
Forked from Wan-Video/Wan2.1A fast AI Video Generator for the GPU Poor. Supports Minimax H3, LTX-2.3/2.5, Wan 2.1/2.2, Qwen Image 1/2, Krea 2, Hunyuan Video, LTX Video and Flux.
A LLM trained only on data from certain time periods to reduce modern bias
An interactive visualization for exploring 17 years of Comedy Bang Bang podcast data
Z-Image, Flux2 Klein, Krea2 & SeedVR2 with a Gradio UI. Uses a built-in ComfyUI backend for speed and efficiency! [8GB+VRAM, 16GB+ RAM]
Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints.
Real-time Visualizer for Neural Networks
ComfyUI utility nodes for Z-Image model. Features LLM-powered prompt enhancement using the official Z-Image system prompt.
This is the repository where some contour based game's codes and notebooks are stored. For more information please visit acharyaramkrishna.com.np
An agent that can run everywhere - even in your watch!
Real-time offline speech-to-text transcription script on macOS using parakeet-mlx
[CVPR 2026 Highlight] Official Implementations for Paper - HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives
All in one Image/video/sound editor/upscaler/creator
An experiment that applies Google Research's `ReasoningBank` technique to Small Language Models. This experiment hopes to show that the same gains from the ReasoningBank paper also applies to much …
Real (ish) time Chat TTS -> LLM -> STT Local
🤗 smolagents: a barebones library for agents that think in code.
Multi-Platform Package Manager for Stable Diffusion