sdbds / SageAttention-for-windowsLinks
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.
☆46Updated 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
Sorting:
- 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…☆58Updated 8 months ago
- Divide and Conquer Node Suite☆82Updated 3 weeks ago
- A video clipper for Hunyuan video training.☆82Updated last week
- Load your model with image previews, or directly download and import Civitai models via URL. This custom ComfyUI node supports Checkpoint…☆46Updated 11 months ago
- ComfyUI-FreeMemory is a custom node extension for ComfyUI that provides memory management capabilities within your image generation workf…☆110Updated 4 months ago
- This is a pre-built wheel of Triton 3.3.0 for Windows with Nvidia only + Proton☆27Updated 2 months ago
- ☆82Updated 3 months ago
- ☆117Updated 2 months ago
- Janky implementation of HiDiffusion for ComfyUI☆122Updated 3 months ago
- NNT Neural Network Toolkit Custom Nodes for ComfyUI☆69Updated 7 months ago
- ComfyUI Implementaion of ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment☆159Updated last year
- Custom node for ComfyUI. Add a node to save images with metadata (PNGInfo) extracted from the input values of each node.☆92Updated 4 months ago
- flux distillation and stuff☆114Updated last month
- This workflow experiments with image detailing using a mix of techniques like latent space manipulation and interpolation. I've been play…☆109Updated 11 months ago
- Comfy UI nodes for Flex.1☆69Updated 3 months ago
- ☆141Updated 3 months ago
- ExLlamaV2 nodes for ComfyUI.☆119Updated 8 months ago
- ☆62Updated 2 months ago
- ComfyUI Wrapper for HiDream - 4bit linux loading fix☆98Updated 2 months ago
- ComfyUI style LDM patching in A1111☆53Updated last year
- The IMAGE-interrogator for SOTA image captioning☆83Updated last year
- Run Local and API LLMs, Features Gemini2 image generation, DEEPSEEK R1, QwenVL2.5, QWQ32B, Ollama, LlamaCPP LMstudio, Koboldcpp, TextGen,…☆132Updated 4 months ago
- Executable Stable Diffusion merge recipes in comfyui☆85Updated last week
- Save/Load trigger words for loras from a json and auto fetch them on civitai if they are missing. Optional prompt input to auto append th…☆79Updated 5 months ago
- Attention Couple, NegPip (negative weights in prompts) for SDXL, FLUX and HunyuanVideo, more CFG++ and SMEA DY samplers, etc.☆209Updated last month
- A Prompt Enhancer for flux.1 in ComfyUI☆112Updated this week
- ComfyUI nodes collection: better TAESD previews (including batch previews), improved HyperTile and Deep Shrink nodes☆114Updated last month
- Node to load LLM, it can be used to generate prompt or enhance them☆65Updated 3 months ago
- it really is a skill issue☆33Updated last year
- An Extension for Automatic1111 Webui that increases/decreases the details of images☆83Updated 11 months ago