oobabooga / flash-attentionLinks
Fast and memory-efficient exact attention - Windows wheels
☆36Updated 6 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:
- ☆32Updated last year
- This is a pre-built wheel of Triton 3.3.0 for Windows with Nvidia only + Proton☆39Updated 6 months ago
- This is a simple node for comfyUI that accesses any openAI API server the user specifies and enables simple text generation with a string…☆27Updated last year
- Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossi…☆78Updated last week
- A repository of extra samplers, usable within ComfyUI for most nodes.☆95Updated last year
- A ComfyUI implementation of Meta AI's AITemplate repo for faster inference using cpp/cuda.☆51Updated last year
- ExLlamaV2 nodes for ComfyUI.☆119Updated 11 months ago
- Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (PRG)☆52Updated last year
- ☆96Updated 6 months ago
- Development repository for the Triton language and compiler☆33Updated last year
- Janky implementation of HiDiffusion for ComfyUI☆125Updated 6 months ago
- Training and generation / detection / inference scripts dealing with Yolov8☆70Updated last year
- An Extension for Automatic1111 Webui that helps inserting prompts☆52Updated 8 months ago
- ☆118Updated 2 years ago
- Batched Runge-Kutta Samplers for ComfyUI☆62Updated last year
- Executable Stable Diffusion merge recipes in comfyui☆94Updated last week
- ComfyUI style LDM patching in A1111☆53Updated last year
- flux distillation and stuff☆120Updated 4 months ago
- ComfyUI powertools for SD1.5 and SDXL model merging☆92Updated 7 months ago
- Node to load LLM, it can be used to generate prompt or enhance them☆66Updated 7 months ago
- ☆139Updated 7 months ago
- A system for Prompt generation to improve Text-to-Image performance.☆86Updated 8 months ago
- ☆71Updated 6 months ago
- A convenient fast Text to Speech Whisper Speech by Collabora you can train a voice on the fly on ComfyUI☆44Updated 8 months ago
- ☆73Updated last year
- This workflow experiments with image detailing using a mix of techniques like latent space manipulation and interpolation. I've been play…☆110Updated last year
- AegisFlow XL and AegisFlow 1.5 are ComfyUI workflows designed by a professional for professionals☆35Updated last year
- This is a repository for "character images search" from image and tags.☆36Updated 2 months ago
- Provide large guidance scale correction for Stable Diffusion web UI (AUTOMATIC1111), implementing the paper "Characteristic Guidance: Non…☆83Updated 8 months ago
- a custom comfyui node for coqui-ai/TTS's xtts module! support 17 languages voice cloning and tts☆63Updated last year