Fast and memory-efficient exact attention
☆893Dec 9, 2025Updated 3 months ago
Alternatives and similar repositories for flash-attention
Users that are interested in flash-attention are comparing it to the libraries listed below
Sorting:
- Fork of the Triton language and compiler for Windows support and easy installation☆1,869Feb 18, 2026Updated 2 weeks ago
- Fast and memory-efficient exact attention - Windows wheels☆36Apr 30, 2025Updated 10 months ago
- Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossi…☆119Jan 26, 2026Updated last month
- Fork of SageAttention for Windows wheels and easy installation☆734Feb 15, 2026Updated 3 weeks ago
- Fast and memory-efficient exact attention☆40Updated this week
- Windows compile of bitsandbytes for use in text-generation-webui.☆361Nov 18, 2023Updated 2 years ago
- Pre-compiled Python whl for Flash-attention, SageAttention, NATTEN, xFormer etc☆537Feb 26, 2026Updated last week
- Fast and memory-efficient exact attention☆22,460Updated this week
- A set of nodes for ComfyUI that can composite layer and mask to achieve Photoshop like functionality.☆2,917Jan 30, 2026Updated last month
- for tile the image for advanced control or modification☆951Jan 8, 2026Updated 2 months ago
- This is a pre-built wheel of Triton 3.3.0 for Windows with Nvidia only + Proton☆40May 18, 2025Updated 9 months ago
- ☆195Jul 31, 2024Updated last year
- ☆109Dec 20, 2024Updated last year
- GGUF Quantization support for native ComfyUI models☆3,348Jan 12, 2026Updated last month
- Support for miscellaneous image models. Currently supports: DiT, PixArt, T5 and a few custom VAEs☆18May 20, 2024Updated last year
- ☆479Oct 30, 2024Updated last year
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,716Updated this week
- ☆64Feb 14, 2026Updated 3 weeks ago
- Flash Attention 2 pre-built wheels for Windows. Drop-in replacement for PyTorch attention providing up to 10x speedup and 20x memory redu…☆36Dec 1, 2024Updated last year
- ComfyUI BrushNet nodes☆937Mar 31, 2025Updated 11 months ago
- Support for miscellaneous image models. Currently supports: DiT, PixArt, HunYuanDiT, MiaoBi, and a few VAEs.☆533Dec 17, 2024Updated last year
- Diffusers wrapper to run Kwai-Kolors model☆597Oct 18, 2024Updated last year
- Generate detailed image descriptions and analysis using Molmo models in ComfyUI.☆140Oct 14, 2024Updated last year
- Inference Microsoft Florence2 VLM☆1,615Jan 30, 2026Updated last month
- nunchaku0.3.0.dev2的各种轮子列表☆41May 20, 2025Updated 9 months ago
- Multimodal captioner☆218Updated this week
- SUPIR upscaling wrapper for ComfyUI☆2,234Feb 4, 2026Updated last month
- Recommended based on comfyui node pictures:Joy_caption + MiniCPMv2_6-prompt-generator + florence2☆621Feb 6, 2025Updated last year
- ☆158Mar 19, 2025Updated 11 months ago
- ☆512Apr 26, 2025Updated 10 months ago
- ComfyUI Node☆714Jun 18, 2025Updated 8 months ago
- ☆1,543Aug 7, 2025Updated 7 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,192Jan 17, 2026Updated last month
- Programmable Module and CLI for converting images to seamless tiles☆15Sep 8, 2024Updated last year
- ☆6,148Feb 22, 2026Updated 2 weeks ago
- ComfyUI nodes to use segment-anything-2☆1,178Sep 28, 2025Updated 5 months ago
- ACE-Step: A Step Towards Music Generation Foundation Model☆232May 28, 2025Updated 9 months ago
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆1,219Aug 2, 2025Updated 7 months ago
- Accelerate inference in Flux and Sana for ComfyUI.☆222Mar 13, 2025Updated 11 months ago