Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip selected H3 transformer evaluations, with adaptive scheduling, sampler-aware support for Euler, ER-SDE, RES, SEEDS and SA-Solver, CPU/VRAM history storage, and fail-closed native fallbacks.
☆625Sep 2, 2026Updated this week
Alternatives and similar repositories for ComfyUI-Spectrum-MiniMax-H3
Users that are interested in ComfyUI-Spectrum-MiniMax-H3 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 分享V2Ray、SSR、SS☆10Dec 7, 2020Updated 5 years ago
- Brand new TTS solution☆11Dec 7, 2024Updated last year
- TypeScript/Node.js bindings for Apple's on-device Foundation Models (macOS 26+ only)☆20Aug 28, 2026Updated last week
- Custom nodes for ComfyUI to generate empty latent space compatible with Hunyuan models for both image and video generation.☆10Dec 29, 2024Updated last year
- Interactive visualizations and RAG mining report from the November 2025 House Oversight Epstein document release☆17Nov 27, 2025Updated 9 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Conversion of JavaScript's Array methods to AutoHotkey☆11May 11, 2018Updated 8 years ago
- The sorce code for the realtime video descriptors: HOG, HOF, MBH and HMG☆10Feb 6, 2017Updated 9 years ago
- Full stack data-science project☆12Jan 13, 2022Updated 4 years ago
- An MCP server for schema.org☆21Jul 13, 2026Updated last month
- Live-codeable synths and mini-notation patterns in the browser, with a from-scratch AudioWorklet DSP engine.☆67Updated this week
- Detecting faces using MLKit☆10Aug 8, 2019Updated 7 years ago
- ☆12Jul 6, 2026Updated last month
- A beautiful, native Markdown viewer and lightweight editor for macOS and Windows. ~8MB, free, open source.☆131Aug 26, 2026Updated last week
- XJGARSDK是一个免费的跨平台实时视频处理库，只需学会一套API就可以在MAC、Windows、Linux、IOS、Android等主流操作系统，提供了业界领先的视频磨皮美颜、视频滤镜、人脸实时整形（瘦脸、大眼睛等）、人脸动态贴纸等功能的库。本项目包含了Windows(…☆15Sep 4, 2019Updated 7 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆10Nov 1, 2018Updated 7 years ago
- 日本語N2ワード（新しい標準日本語初級および中級）☆15Dec 29, 2025Updated 8 months ago
- A self-documenting, progressive discovery API protocol ideal for AI agents.☆24Feb 18, 2026Updated 6 months ago
- Some scripts used for action recognition on UCF101 dataset☆11Dec 2, 2015Updated 10 years ago
- A module apply registry keys using LGPO instead☆13Apr 23, 2023Updated 3 years ago
- Action Recognition in Videos using Stacked Optical Flow and HOGHOF features.☆11May 8, 2017Updated 9 years ago
- Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton based Action Recognition☆11Aug 30, 2021Updated 5 years ago
- pytorch for : Learning Spatiotemporal Features with 3D Convolutional Networks(2015-ICCV)☆11Mar 6, 2020Updated 6 years ago
- ☆16Apr 26, 2021Updated 5 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Face detect demo for AndroidX in java☆11Nov 16, 2021Updated 4 years ago
- A browser extension that builds tab functionality to easily manage your subscriptions on Youtube☆12Aug 5, 2026Updated last month
- This is an implementation of the Unsupervised Learning of Video Representations via Dense Trajectory Clustering algorithm.☆15Jul 29, 2020Updated 6 years ago
- 基于rknn的yolov5的cpp实现，包含各种依赖库，是一个完整工程，可直接编译运行☆20Feb 10, 2022Updated 4 years ago
- SNI proxy with an option to relay traffic to a custom IP address when required☆15Jun 16, 2024Updated 2 years ago
- 参考论文：Guo Y, Chen J, Wang J, et al. Closed-loop matters: Dual regression networks for single image super-resolution[C]//Proceedings of the…☆13Jan 17, 2023Updated 3 years ago
- SeetaFace6 for Android☆14Jan 2, 2024Updated 2 years ago
- Testing code for few-shot action recognition☆11Jan 12, 2021Updated 5 years ago
- Implemented Sports Action Recognition system using SVM classifier. First, extracted the features from each video frame from each categor…☆14Oct 15, 2019Updated 6 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Contains code for C3D, LCN and TSM for action recognition models.☆10May 31, 2020Updated 6 years ago
- Abdominal Organ Segmentation using Multi Decoder Network (MDNet) [Accepted at ICASSP 2025]☆13Apr 15, 2025Updated last year
- ☆18Jan 10, 2023Updated 3 years ago
- Local Group Policy Editor plus more, for all Windows editions☆14Sep 29, 2025Updated 11 months ago
- A Multimodal Facial Biometric System for Recognition, Gender Classification, Emotion Recognition and Face-Shape Prediciton☆20May 22, 2025Updated last year
- Multi-threaded/Multi-Process Downloader for Currency Exchange Rates from Histdata.com☆26Updated this week
- This project is a part of our work, "Dynamic Vision Sensors for Human Activity Recognition" accepted at the IEEE 4th IAPR Asian Conferenc…☆15Feb 18, 2019Updated 7 years ago