Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
Repository Index
47,133 repositories indexed
25–48 of 189 · Most stars
Todas as leis do Brasil
SOTA-Class TTS at Compact Scale
TranslatedAll Administrative Aptitude Test (Xingce) real exam questions from China's civil service exams, both national and provincial, 2016-2026
TranslatedA browser app that automatically assembles a text PV (lyric video) from lyrics
TranslatedHigh-performance · Lightweight · AI Native Video workspace. A video creation workspace for the AI era. On the canvas, freely connect ideas and materials together with the Agent.
- ai-image-generation
- ai-video
- ai-video-generation
- ai-workspace
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees.
A Multilingual, Multimodal Translation Model Family
- llm
- machine-translation
TranslatedA Windows local AI Agent Studio for Douyin live-streaming e-commerce, connecting streamer discovery, live stream insights, live stream review, and short-video content directing into one unified intelligent workflow.
- ai-agent
- douyin
- livestream
- speech-to-text
Local AI song generator with an editable score — YuE2 on your GPU: full songs with vocals, sheet music, covers, exact replay. Native Windows app, no Python, installer with auto-update.
- abc-notation
- ai-music
- covers
- cuda
AI digital-human talking-head videos from one photo: Renoise MCP generation + 5 editing styles + 48 creator-grade packaging components. Agent skill for Claude Code / Codex / OpenClaw / WorkBuddy …
Show it a video you love. Get a new video in the same style. An AI crew (Claude Code or Codex) plans, builds and reviews it with you.
- 2d-animation
- ai-agents
- ai-video
- animation
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
Pika H3 Flex: video and audio generation inference
One-click character swap for videos: an open-source, local Higgsfield Genjutsu alternative built on ComfyUI and MiniMax H3, with FLUX.3 Klein relighting.
- character-swap
- comfyui
- minimax-h3
- nextjs
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
- diffusion-models
- high-resolution
- sparse-attention
- video-generation
NCM: Next Concept Modeling
Official PyTorch inference for Breeze TTS 2
The repository host gives no description.
Open-source AI video replacement workflow by TEIN. Combine depth maps, SAM segmentation, face meshes, and audio processing to replace characters and objects with Seedance. Includes a local web UI to prepare inputs, review masks, preview generations, and export with original audio.
Official PyTorch implementation of VisionHOPE: Visual Backbones as Self-Modifying Learning Systems.
- backbone
- computer-vision
- image-classification
- backbone-networks
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
- evolutionary-algorithms
- rsi-ai
- self-improvement
- llm-agent
Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.