Fork of SageAttention for Windows wheels and easy installation
☆1,049Sep 24, 2026Updated this week
Alternatives and similar repositories for SageAttention
Users that are interested in SageAttention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Fork of the Triton language and compiler for Windows support and easy installation☆1,952Feb 18, 2026Updated 7 months ago
- Pre-compiled Python whl for Flash-attention, SageAttention, NATTEN, xFormer etc☆871Sep 7, 2026Updated 2 weeks ago
- Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossi…☆157Updated this week
- RadialAttention in ComfyUI native workflow☆120Dec 19, 2025Updated 9 months ago
- ComfyUI Plugin of Nunchaku☆2,928Sep 6, 2026Updated 3 weeks ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Fork of SpargeAttention (SparseSageAttention) for Windows wheels and easy installation☆40May 14, 2026Updated 4 months ago
- Official SeedVR2 Video Upscaler for ComfyUI☆2,872Dec 24, 2025Updated 9 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆80Jan 19, 2026Updated 8 months ago
- ☆6,712May 24, 2026Updated 4 months ago
- Various custom nodes for ComfyUI☆3,324Sep 13, 2026Updated 2 weeks ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,950Jan 17, 2026Updated 8 months ago
- ComfyUI-QwenVL custom node: Integrates the Qwen-VL series, including Qwen2.5-VL, Qwen3-VL, Qwen3.5-VL, Qwen3.6-VL (MoE), and Qwen3.8-VL, …☆894Sep 14, 2026Updated 2 weeks ago
- Triton with Windows support☆263Updated this week
- ☆1,338Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- An experimental node☆577Feb 9, 2026Updated 7 months ago
- ☆855Jan 24, 2026Updated 8 months ago
- The successful integration of Qwen3-VL-Instruct series into the ComfyUI platform has enabled a smooth operation, supporting (but not limi…☆584Oct 23, 2025Updated 11 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,957Sep 6, 2026Updated 3 weeks ago
- Efficient Python bindings for the llama.cpp library☆551Updated this week
- ☆166Mar 19, 2025Updated last year
- LoRA Loader & Diffsynth/LoRA ControlNet Loader for Nunchaku Qwen Image & Nunchaku Z-Image Turbo. Krea2 Depth/OpenPose LoRA ControlNet Loa…☆345Sep 14, 2026Updated last week
- Run LLM/VLM models natively in ComfyUI based on llama.cpp☆561Aug 17, 2026Updated last month
- A simple node that can dynamically adjust the reserved memory of a workflow in real-time, used to avoid the utilization of shared memory.☆445Sep 11, 2026Updated 2 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ComfyUI implemtation for NAG☆318Nov 3, 2025Updated 10 months ago
- Comfyui implementation of OpenIXCLab Sec-4B☆378Dec 19, 2025Updated 9 months ago
- Real-Time Diffusion-Based Streaming Video Super-Resolution / 基于Diffusion架构的实时视频流超分模型☆796Nov 20, 2025Updated 10 months ago
- A custom ComfyUI node for MiniCPM vision-language models, supporting v4, v4.5, and v4 GGUF formats, enabling high-quality image captionin…☆156Aug 28, 2025Updated last year
- A ComfyUI custom node for 3D camera angle control. Provides an interactive Three.js viewport to adjust camera angles and outputs formatte…☆1,379Sep 13, 2026Updated 2 weeks ago
- ☆630Mar 18, 2026Updated 6 months ago
- A powerful set of tools for ComfyUI☆1,997Oct 26, 2025Updated 11 months ago
- An enhanced Wan2.2 Image-to-Video node specifically designed to fix the slow-motion issue in 4-step LoRAs (like lightx2v).☆633Aug 1, 2026Updated last month
- Modification of the KSampler for running models like Wan2.2 a14B☆250Oct 22, 2025Updated 11 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆242Aug 25, 2026Updated last month
- The nodes detached from [ComfyUI Layer Style](https://github.com/chflame163/ComfyUI_LayerStyle) are mainly those with complex requirement…☆712Sep 18, 2026Updated last week
- In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.☆2,768Sep 21, 2026Updated last week
- ☆575Feb 1, 2026Updated 7 months ago
- ComfyUI nodes for WanAnimate model input preprocessing☆545May 27, 2026Updated 4 months ago
- for tile the image for advanced control or modification☆1,041Sep 14, 2026Updated 2 weeks ago
- LoRA Manager for ComfyUI - A powerful extension for organizing, previewing, and integrating LoRA models with metadata and workflow suppor…☆1,495Updated this week