Stars
Maps input devices to Virtual Gamepads.
ComfyUI redirection proxy: Forward ComfyUI job/workflow execution to a remote/cloud/serverless GPU endpoint, while workflow editing stays fully local.
Four ComfyUI nodes for MiniMax H3: name your media with @, lock exact dialogue, and get the structured brief H3 wants. No <Picture 1> bookkeeping, no second service to start.
Unity2Blender / TachiyomiAT-1
Forked from mannu691/TachiyomiATFree and open source manga reader for Android
Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.
High quality training free inpaint for every stable diffusion model. Supports ComfyUI
anr2me / modal-comfyui
Forked from caru-ini/modal-comfyuiRun ComfyUI on Modal.com with auto-scaling, GPU snapshots, and easy model management.
A project to generate character portraits from book text using RAG based book search and image generation using local diffusion models.
A modal worker for running comfy workflows as an API
Run ComfyUI on Modal with auto-scaling, GPU snapshots, and easy model management. Try image, video generation via ComfyUI on Modal.
cryptofetch lets you download high-resolution historical crypto candlestick data directly from Binance with zero setup. Features both a sleek terminal CLI and an interactive web app with real-time …
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
High-performance FlashAttention-2 for AMD, Intel, and Apple GPUs. Drop-in replacement for PyTorch SDPA. Triton backend for ROCm (MI300X, RDNA3), Vulkan backend for consumer GPUs. No CUDA required.
High-Performance server for NATS.io, the cloud and edge native messaging system.
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
A sparse attention kernel supporting mix sparse patterns
mannu691 / TachiyomiAT
Forked from mihonapp/mihonFree and open source manga reader for Android
muzuzaki7898 / TachiyomiAT
Forked from mannu691/TachiyomiATFree and open source manga reader for Android
Tiled Diffusion, MultiDiffusion, Mixture of Diffusers, and optimized VAE
ComfyUI-ThinkSound is now available in ComfyUI, ThinkSound is a unified Any2Audio generation framework with flow matching guided by Chain-of-Thought (CoT) reasoning.
Efforts toward giving Qwen 3 Coder 30B A3B proper agentic tool calling capabilities at or near 100% reliability.
ModelTC / LightX2V-Wan2.2-Lightning
Forked from Wan-Video/Wan2.2Wan2.2-Lightning: Speed up wan2.2 model with distillation
This GitHub repository is a guide on using Google Colaboratory as a virtual private server (VPS). It includes instructions on setup and configuration, as well as sample code for various application…
[CVPR 2025] Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment