daswer123 / deepspeed-windows-wheelsView external linksLinks
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
☆86Sep 17, 2024Updated last year
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:
- Light-A-Video: Training-free Video Relighting via Progressive Light Fusion,you can use it in comfyUI☆88Apr 10, 2025Updated 10 months ago
- A very basic port of the stereoscopic script used in thygate/stable-diffusion-webui-depthmap-script☆38Feb 6, 2026Updated last week
- LTX-Video-Trainer-GUI 是为LTX视频lora模型训练提供的GUI工具，支持通过简单的界面训练 LoRA 模型用于视频生成。本训练器提供了直观的 GUI 界面，使用户能够轻松设置和启动训练流程，无需编写复杂代码。☆13Jul 18, 2025Updated 6 months ago
- ☆15Nov 11, 2024Updated last year
- Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis☆27Mar 21, 2025Updated 10 months ago
- Scripts help setup a clean install of ComfyUI and supporting tools☆25Aug 19, 2024Updated last year
- Using CogVLM and CogAgent for image captioning☆15Dec 29, 2023Updated 2 years ago
- ☆18Dec 30, 2024Updated last year
- Grams: Gradient Descent with Adaptive Momentum Scaling (ICLR 2025 Workshop)☆17Mar 6, 2025Updated 11 months ago
- gradio web ui for musepose☆15Jun 29, 2024Updated last year
- FlowMirror-HydraVox — A natively accelerated multi-head autoregressive TTS system derived from CosyVoice 3.0. It predicts multiple tokens…☆38Jan 22, 2026Updated 3 weeks ago
- ComfyUI nodes using uses local vision LLMs / VLMs (and other providers) optimized for wan2.2, wan2.1, and flux kontext. with pushdown ima…☆21Sep 30, 2025Updated 4 months ago
- An extension for ComfyUI to add IPAdapter nodes for clip vision model with different input size.☆17Feb 9, 2025Updated last year
- ComfyUI nodes for StableAnimator☆17Apr 24, 2025Updated 9 months ago
- This project is based on SadTalker to implement video lip synthesis.☆15Jan 9, 2024Updated 2 years ago
- ☆14Jun 23, 2024Updated 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…☆114Jan 26, 2026Updated 2 weeks ago
- face swap Rope, wrap for ComfyUI☆21Jan 7, 2025Updated last year
- ☆19Jul 31, 2024Updated last year
- Signal Processing Nodes For ComfyUI☆19May 14, 2025Updated 9 months ago
- Python package to download FFmpeg binaries from distro servers☆18Nov 14, 2025Updated 3 months ago
- Side by Side Stereoscope node for ComfyUI by SamSeen☆46Jan 18, 2026Updated 3 weeks ago
- A ComfyUI wrapper for Diffusion Self Distillation (DSD) - Zero-Shot Customized Image Generation☆42Mar 15, 2025Updated 10 months ago
- A ComfyUI node containing multiple audio processing tools.☆84Jul 7, 2025Updated 7 months ago
- Crowdsourced and Automatic Speech Prominence Estimation☆24Apr 12, 2024Updated last year
- Custom ComfyUI nodes for downloading, converting, and previewing audio/video from YouTube and 1,000+ other platforms☆29Sep 6, 2025Updated 5 months ago
- A python program for adding new game / multiple character support to Steam games☆15Apr 12, 2024Updated last year
- The IMAGE-interrogator for SOTA image captioning☆85Apr 17, 2024Updated last year
- [EMNLP 2025 Findings] Official code for EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion☆33Sep 9, 2025Updated 5 months ago
- Portrait Tools: Facial detection cropping, alignment, ID photo, etc☆19Jun 15, 2025Updated 7 months ago
- Fast and memory-efficient exact attention☆37Jan 26, 2026Updated 2 weeks ago
- Python GUI tool for preparing video datasets (LORA, Wan, Hunyuan training). Features range clipping, cropping, FPS conversion & optional …☆95Jun 2, 2025Updated 8 months ago
- A LoRa loader for ComfyUI that allows automatic storage and retrieval of trigger words☆34Dec 23, 2025Updated last month
- ☆57Dec 25, 2025Updated last month
- Creates prompts for Video Models by sequence analysis and prompting using Qwen2.5-VL models from Alibaba.☆53Apr 2, 2025Updated 10 months ago
- This node creates a sequence of frames by moving and scaling a subject image over a background image.☆22May 23, 2024Updated last year
- ComfyUI custom nodes for Diffusion Attentive Attribution Maps (DAAM)☆43Oct 13, 2025Updated 4 months ago
- A comprehensive, click to install, fully open-source, Video + Audio Generation AIO Toolkit using advanced prompt engineering plus the po…☆21Dec 20, 2024Updated last year
- A collection of custom nodes for ComfyUI.☆28Jun 28, 2025Updated 7 months ago