kingbri1 / flash-attention
Fast and memory-efficient exact attention
☆453Updated last month
Alternatives and similar repositories for flash-attention:
Users that are interested in flash-attention are comparing it to the libraries listed below
- Fork of the Triton language and compiler for Windows support and easy installation☆755Updated this week
- Windows compile of bitsandbytes for use in text-generation-webui.☆350Updated last year
- You can using EchoMimic in ComfyUI☆597Updated 3 weeks ago
- Inference Microsoft Florence2 VLM☆1,076Updated this week
- ☆511Updated 2 months ago
- ComfyUI nodes for Janus-Pro, a unified multimodal understanding and generation framework.☆558Updated last month
- ☆247Updated 10 months ago
- a comfyui custom node for GPT-SoVITS! you can voice cloning and tts in comfyui now☆222Updated 7 months ago
- Phi3 中文仓库☆320Updated 4 months ago
- Unofficial implementation of YOLO-World + EfficientSAM for ComfyUI☆704Updated 10 months ago
- a comfyui custom node for CosyVoice☆245Updated 6 months ago
- Diffusers wrapper to run Kwai-Kolors model☆589Updated 5 months ago
- ☆388Updated 7 months ago
- ☆362Updated 4 months ago
- Recommended based on comfyui node pictures:Joy_caption + MiniCPMv2_6-prompt-generator + florence2☆539Updated last month
- You can using StoryDiffusion in ComfyUI☆318Updated this week
- hf-mirror-cli 使用国内镜像，无需配置开箱即用，快速下载hugingface上的模型☆129Updated last month
- Kolors的ComfyUI原生采样器实现(Kolors ComfyUI Native Sampler Implementation)☆561Updated 2 months ago
- GOT-OCR的GUI版本，提供OCR、导出PDF、批处理等功能，但不提供训练功能☆161Updated this week
- 这个工具利用Ollama的多个视觉模型，高效地对图片进行打标，并通过AI进行润色优化。如果你觉得对大量图片进行打标是一件繁琐的事情，那么这个工具就是为你量身打造的。 主要特点： 多模型打标：利用各种开源模型，同时对图片进行打标。 AI润色：自动优化和润色已打标的图片。 成…☆53Updated 8 months ago
- comfyui节点文档插件,enjoy~~☆203Updated this week
- The implementation of MiniCPM-V-2_6-int4 has been seamlessly integrated into the ComfyUI platform, enabling the support for text-based q…☆172Updated 6 months ago
- 一个用于CosyVoice的api接口项目☆247Updated 2 months ago
- ☆520Updated last month
- LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,a…☆1,537Updated this week
- Support for miscellaneous image models. Currently supports: DiT, PixArt, HunYuanDiT, MiaoBi, and a few VAEs.☆489Updated 3 months ago
- Next-Token Prediction is All You Need☆2,042Updated last week
- ☆366Updated last month
- ☆53Updated 3 months ago
- QWen-VL-Plus & QWen-VL-Max in ComfyUI☆201Updated 10 months ago