Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.
☆157Sep 24, 2026Updated this week
Alternatives and similar repositories for SageAttention-for-windows
Users that are interested in SageAttention-for-windows 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 SageAttention for Windows wheels and easy installation☆1,049Updated this week
- 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
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆80Jan 19, 2026Updated 8 months ago
- Fork of SpargeAttention (SparseSageAttention) for Windows wheels and easy installation☆40May 14, 2026Updated 4 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Fast and memory-efficient exact attention☆57Sep 21, 2026Updated last week
- a set of utils for comfyui lora operation☆33Apr 14, 2026Updated 5 months ago
- A ComfyUI speech recognition plugin based on [Qwen3-ASR](https://github.com/QwenLM/Qwen3-ASR).☆37Feb 6, 2026Updated 7 months ago
- This is a pre-built wheel of Triton 3.3.0 for Windows with Nvidia only + Proton☆44May 18, 2025Updated last year
- RadialAttention in ComfyUI native workflow☆120Dec 19, 2025Updated 9 months ago
- ComfyUI node to assist with Bernini video editing prompting (Ollama + Prompt Presets)☆139Jun 12, 2026Updated 3 months ago
- FSampler is a training‑free, sampler‑agnostic acceleration layer for diffusion sampling.☆134Feb 28, 2026Updated 7 months ago
- Comfy UI Nodes for Krea 2 LoRAs trained with AI Toolkit Experimental Edit☆340Jul 17, 2026Updated 2 months ago
- ☆111Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Fast kernel library for Diffusion inference with multiple compute backends.☆228Updated this week
- ☆1,338Updated this week
- FlashVSR：Towards Real-Time Diffusion-Based Streaming Video Super-Resolution，you can use it in comfyUI☆397Feb 23, 2026Updated 7 months ago
- A ComfyUI node implementation for ByteDance's Sa2VA☆95Dec 22, 2025Updated 9 months ago
- HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.☆114May 28, 2026Updated 4 months ago
- ☆630Mar 18, 2026Updated 6 months ago
- ☆187Aug 30, 2026Updated 3 weeks ago
- LucidFlux: Caption-Free Universal Image Restoration with a Large-Scale Diffusion Transformer，you can use it in ComfyUI☆62May 27, 2026Updated 4 months ago
- An experimental node☆577Feb 9, 2026Updated 7 months 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.
- ☆165Jun 27, 2026Updated 3 months ago
- ☆166Mar 19, 2025Updated last year
- ☆242Aug 25, 2026Updated last month
- Run LLM/VLM models natively in ComfyUI based on llama.cpp☆561Aug 17, 2026Updated last month
- ComfyUI nodes for SCAIL-Pose preprocessing☆321Apr 15, 2026Updated 5 months ago
- ☆484May 20, 2026Updated 4 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
- ☆192Dec 24, 2025Updated 9 months ago
- HunyuanVideoFoley generates SFX audio to match your video and text prompt☆178Sep 8, 2025Updated last year
- 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.
- Mel-Band RoFormer for Music Source Separation☆257Jan 30, 2026Updated 7 months ago
- A family of highly efficient, lightweight yet powerful optimizers.☆36Updated this week
- Standalone ComfyUI plugin for Wan 2.2 Bernini video generation and editing.☆135Sep 10, 2026Updated 2 weeks 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
- ☆121May 22, 2024Updated 2 years ago
- Seed-VC voice or sing conversion.☆67Jun 11, 2025Updated last year
- Clean up system cache, support VRAM cleaning and RAM cleaning☆401Jan 12, 2026Updated 8 months ago