oobabooga / flash-attentionLinks
Fast and memory-efficient exact attention - Windows wheels
☆36Updated 5 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:
- This is a pre-built wheel of Triton 3.3.0 for Windows with Nvidia only + Proton☆38Updated 5 months ago
- A ComfyUI implementation of Meta AI's AITemplate repo for faster inference using cpp/cuda.☆51Updated last year
- 8-bit CUDA functions for PyTorch☆25Updated 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…☆70Updated this week
- An Extension for Automatic1111 Webui that helps inserting prompts☆52Updated 7 months ago
- Stable Diffusion PNGINFO Beautify extension☆28Updated last week
- ☆27Updated 6 months ago
- Flux Fill 1.0 GO: flux Inpainting and outpainting starting with 8Gb of VRAM☆69Updated 9 months ago
- ☆90Updated 5 months ago
- ExLlamaV2 nodes for ComfyUI.☆120Updated 10 months ago
- An image viewer and AI-assisted editing/captioning/masking tool that helps with curating datasets for generative AI models, finetunes and…☆135Updated last week
- Provide large guidance scale correction for Stable Diffusion web UI (AUTOMATIC1111), implementing the paper "Characteristic Guidance: Non…☆83Updated 7 months ago
- SD.Next ModernUI☆36Updated this week
- flux distillation and stuff☆119Updated 3 months ago
- Adaptive ODE Solvers for ComfyUI☆52Updated last year
- ComfyUI style LDM patching in A1111☆52Updated last year
- Supercharge your AI/LLM prompts☆78Updated 11 months ago
- Executable Stable Diffusion merge recipes in comfyui☆92Updated 2 weeks ago
- Text to Img with Stable Cascade(on gradio interface), required less vram than original example on official Hugginface☆38Updated last year
- ☆32Updated last year
- Processes SafeTensors files for Stable Diffusion 1.5 (SD 1.5), Stable Diffusion XL (SDXL), and FLUX models. It extracts the UNet into a s…☆59Updated 11 months ago
- A collection of compiled wheels for deepspeed built for python 3.10 and 3.11 with support for cuda 11.8 and 12.1 for Windows☆73Updated last year
- ComfyUI Node for FlashFace☆68Updated 7 months ago
- ☆12Updated last year
- Node to load LLM, it can be used to generate prompt or enhance them☆65Updated 6 months ago
- The IMAGE-interrogator for SOTA image captioning☆84Updated last year
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆62Updated 7 months ago
- Batched Runge-Kutta Samplers for ComfyUI☆61Updated last year
- NNT Neural Network Toolkit Custom Nodes for ComfyUI☆68Updated 9 months ago
- Run Stable diffusion 3 on low VRAM systems☆28Updated last year