daswer123 / deepspeed-windows-wheelsLinks
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
☆66Updated 8 months ago
Alternatives and similar repositories for deepspeed-windows-wheels
Users that are interested in deepspeed-windows-wheels are comparing it to the libraries listed below
Sorting:
- Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossi…☆34Updated this week
- This is a pre-built wheel of Triton 3.3.0 for Windows with Nvidia only + Proton☆24Updated 2 weeks ago
- Superprompt a 77M Parameter T5 custom trained checkpoint to make dull prompts detailed.☆68Updated last year
- Zero-Shot Speech Editing and Text-to-Speech in the Wild☆52Updated last year
- flux distillation and stuff☆103Updated this week
- AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation☆37Updated last year
- Deepspeed windows information☆38Updated last year
- GUI for the new musubi-tuner☆36Updated 4 months ago
- A minimal port of the inference functionalities of the original SyncTalk, which uses NeRF based technology that creates a talking head wi…☆39Updated 8 months ago
- ☆68Updated last month
- 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…☆56Updated 6 months ago
- Janky implementation of HiDiffusion for ComfyUI☆121Updated last month
- ☆39Updated 8 months ago
- ☆36Updated 3 months ago
- ☆22Updated last month
- Text Encoders finally matter 🤖🎥 - scale CLIP & LLM influence! + a Nerdy Transformer Shuffle node☆66Updated 4 months ago
- ☆13Updated 4 months ago
- ☆23Updated last year
- the comfyui custom node for UVR5 to separate vocals and background music☆95Updated 11 months ago
- A system for Prompt generation to improve Text-to-Image performance.☆79Updated 2 months ago
- ComfyUI powertools for SD1.5 and SDXL model merging☆86Updated 2 months ago
- ☆143Updated last month
- it really is a skill issue☆33Updated 11 months ago
- understanding human preference in text-to-image synthesis☆31Updated 11 months ago
- Utility nodes for ComfyUI☆63Updated 2 months ago
- ComfyUI wrapper for Kokoro-onnx☆35Updated 4 months ago
- The IMAGE-interrogator for SOTA image captioning☆83Updated last year
- Unofficial implementation of AnyText for ComfyUI(EXP)☆57Updated last year
- ComfyUI implementation of FLATTEN☆108Updated 9 months ago
- Extended Musubi Tuner with latent previews, fp16 accumulation, advanced cfg scheduling and more☆15Updated this week