Stars
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
"Adaptive Hybrid Quantization Framework for deploying 7B+ LLMs on low-VRAM devices (e.g., GTX 1050). Features surgical block alignment and Numba-accelerated inference.
This workflow uses Wan VACE (Wan 2.2 Fun VACE or Wan 2.1 VACE, your choice!) to smooth out awkward motion transitions between video clips. If you have noisy frames at the start or end of your clips…
The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how t…
Native and Compact Structured Latents for 3D Generation
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".
Quick OutputLists from multiline textstrings, number ranges or JSON for sequential processing. Inspect COMBO to make lists from sampler, scheduler, LoRas, models etc. Combinations of lists and prom…
Custom ComfyUI nodes using pytorch360convert
ComfyUI DyPE, enabling artifact-free 4K+ image generation for Qwen, Flux + Nunchacku
Train and block edit and save LoRAs directly inside ComfyUI for Z-image Turbo, SDXL, Flux, WAN 2.2, SD 1.5
ultimate openpose editor with render
JamePeng / llama-cpp-python
Forked from abetlen/llama-cpp-pythonPython bindings for llama.cpp
ComfyUI custom nodes to re-use and stitch together existing prompts.
TGB’s ComfyUI sidecodes showcase key development takeaways—small, powerful nodes like ModelSamplingFluxGradual, PolyExponentialSigmaAdder, BasicSchedulerNormalized, LogSigmaSamplerNode, LogSigmaSte…
A port of muerrilla's sd-webui-Detail-Daemon as a node for ComfyUI, to adjust sigmas that control detail.
Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints.
a set of utils for comfyui lora operation
ComfyUI custom node to extend Wan videos in loops with overlap consistency, per loop prompts, and optional LoRA control.
A ComfyUI node implementation for ByteDance's Sa2VA
InSPyreNet with option to keep weights on GPU
ComfyUI wrapper node for Hunyuan3D-Omni
The ultimate text processing suite for ComfyUI. Now features Batch Cleaning, LLM Parsing, Dynamic Wildcards, and Logic Tools for sophisticated automation.
ComfyUI wrapper for segment anything 3
ComfyUI-TBG-SAM3 A plug-and-play ComfyUI extension providing production-ready nodes for Meta’s SAM3 (Segment Anything Model 3) for text- or point-based segmentation, exhaustive mask generation, and…
[SIGGRAPH ASIA 2025] Code for PartUV: Part-Based UV Unwrapping of 3D Meshes
Ultra fast frame interpolation using Rife Tensorrt inside ComfyUI