minimax-h3 repositories

Trending repositories tagged minimax-h3, ranked by trending score. Updated daily.

  1. 1
    FlashML-org/FreeVideo

    Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.

    GitHub · Python · 4,078 stars · 573 forks · +475 stars in 24 hours · Trending score 4.88

  2. 2
    Keys-Wasserman/Imagination-Studio-by-keys-Wasserman

    Imagination Studio by keys+Wasserman powered by TensorFold: an AI film studio for Mac and NVIDIA DGX Spark. Plan a film like a crew (Slate workflow by Sam Wasserman), render Qwen-Image-2.1 / FLUX3-K pictures and MiniMax H3 / FastH3 video with sound on TensorFold.

    GitHub · Python · 1,210 stars · 224 forks · +26 stars in 24 hours · Trending score 3.38

  3. 3
    D3voz/openjutsu

    One-click character swap for videos: an open-source, local Higgsfield Genjutsu alternative built on ComfyUI and MiniMax H3, with FLUX.3 Klein relighting.

    GitHub · TypeScript · 2,531 stars · 397 forks · +35 stars in 24 hours · Trending score 3.27

  4. 4
    looplj/reveric

    Agent Native 一站式 AI 小说,短剧桌面创作工作台

    GitHub · Dart · 935 stars · 230 forks · +25 stars in 24 hours · Trending score 2.92

  5. 5
    verl-project/verl-omni

    Multimodal RL training framework for diffusion & omni models

    GitHub · Python · 1,561 stars · 337 forks · +17 stars in 24 hours · Trending score 2.66

  6. 6
    akatz-ai/h3-relay

    Steerable, resumable, bounded-memory MiniMax H3 video workflows for ComfyUI

    GitHub · Python · 60 stars · 4 forks · +36 stars in 24 hours · Trending score 2.56

  7. 7
    BeatAPI/awesome-minimax-h3-prompts

    🎬 Curated MiniMax H3 video generation prompts — cinematic, ads, anime, UGC, product videos, and more. Includes playable examples and creator attribution.

    GitHub · JavaScript · 222 stars · 15 forks · +33 stars in 24 hours · Trending score 2.56

  8. 8
    AbrahamPaulJ/nightmare-mobile

    On-device, ComfyUI-style node graph for image/video diffusion on Android. Run MiniMax H3 and WAN 2.2 14B on the Qualcomm Hexagon NPU. SD1.5, SDXL, Flux, Z-Image, Anima, Qwen Image 2.1, Krea 2 & MOSS Image. Inpainting, outpainting, ControlNet, LoRA, IP-Adapter & LivePortrait. Fully offline, no server, no account.

    GitHub · Kotlin · 290 stars · 24 forks · +19 stars in 24 hours · Trending score 2.48

  9. 9
    SwotAtmk/infinite-creation

    infinite-creation 是一个通过提交小说/剧本,本地ComfyUI-MiniMaxH3+Agent+Skill技能全自动无限生产视频,不限时长。

    GitHub · JavaScript · 385 stars · 88 forks · +12 stars in 24 hours · Trending score 2.43

  10. 10
    veda-sparse/Miowtion

    Sparse acceleration and LoRA fine-tuning of MiniMax-H3 on resource-constrained machines.

    GitHub · Python · 62 stars · 6 forks · +24 stars in 24 hours · Trending score 2.33

  11. 11
    igorls/comfyui-h3-editor

    A timeline video editor for MiniMax H3 inside ComfyUI: write shots, render them on your own GPU, cut picture and sound together, or let an agent make the video.

    GitHub · Python · 110 stars · 20 forks · +6 stars in 24 hours · Trending score 2.22

  12. 12
    mrbizarro/Phosphene

    Phosphene is a free, open-source Mac app for making AI videos, pictures, speech and songs offline. Run LTX-2.5 and MiniMax H3 (Hailuo) locally on Apple Silicon: text-to-video and image-to-video with sound, lip-sync, character LoRA training. Mac app or Pinokio. No cloud, no API key, no NVIDIA GPU. Works with Claude Code, Codex and any MCP agent.

    GitHub · Python · 452 stars · 66 forks · +6 stars in 24 hours · Trending score 2.14

  13. 13
    Video-Rebirth/ComfyUI-HyperFlow-Flash

    ComfyUI custom nodes and workflow templates for HyperFlow H3 Flash GGUF checkpoints

    GitHub · Python · 114 stars · 21 forks · +6 stars in 24 hours · Trending score 2.04

  14. 14
    alexturkey/VideoTurko

    MiniMax H3 on a 4 GB GTX 1050 Ti: stable-diffusion.cpp memory patches, up to 209 frames (8.7 s) in one pass

    GitHub · Python · 89 stars · 20 forks · +36 stars in 24 hours · Trending score 1.78

  15. 15
    alaintural/synctile-h3

    MiniMax H3: seam-free 1080p to 4K via synchronized tiles (SyncTile). ComfyUI node + workflow, scene-file Studio, 4.9x faster generation, benchmarks.

    GitHub · Python · 24 stars · 2 forks · +11 stars in 24 hours · Trending score 1.76

  16. 16
    Pixelailabs/ComfyUI-H3-FaceFix-PixelAILabs

    Fix melted, blurry far faces in MiniMax H3 videos in ComfyUI. No re-render, original audio kept. Workflow + H3 Face Size Fade node by PixelAI Labs.

    GitHub · Python · 30 stars · 3 forks · +22 stars in 24 hours · Trending score 1.67

  17. 17
    Video-Rebirth/hyperflow-h3-flash

    HyperFlow H3 Flash: Video Rebirth's 13.7B, 4- to 8-step compressed MiniMax-H3 for joint video and audio generation (INT8 and GGUF)

    GitHub · Python · 241 stars · 17 forks · +3 stars in 24 hours · Trending score 1.65

  18. 18
    JGRFW/comfyui-AICG3D

    短剧工作台 | 无限时长视频的 MiniMax H3 工作流 | ComfyUI 本地短剧与长视频生成插件

    GitHub · Python · 546 stars · 80 forks · 0 stars in 24 hours · Trending score 1.65

  19. 19
    lifeidle/comfyui-5090-laptop-24gb-minimax-h3-qwen-image-wan2.2

    RTX 5090 Laptop (24GB) + ComfyUI: 12 model lines / 21 measured configs — MiniMax H3, Wan 2.2, Qwen-Image 2512, HunyuanVideo 1.5, FLUX.2 Klein, Z-Image-Turbo, LTX-Video, ACE-Step 1.5, YuE2, Stable Audio 3, Hunyuan3D 2.1, ERNIE-Image. A controlled A/B proves NVFP4 beats INT8. Bilingual 中文/English, licence-verified.

    GitHub · HTML · 26 stars · 0 forks · +10 stars in 24 hours · Trending score 1.62

  20. 20
    SonderSaid/ComfyUI-Sonder-Editor

    Timeline-based video editor for ComfyUI with scenes, project assets, gallery, images as keyframes, render staging, and takes for iterative long-form generation.

    GitHub · Python · 55 stars · 11 forks · +7 stars in 24 hours · Trending score 1.60

  21. 21
    1113800942/comfy-h3md-director

    ComfyUI nodes for long MiniMax H3 video: 2+ minutes at 1080p in one run, seamless long takes with Chained Context Windows (CCW), multi-shot Director, motion copy, redraw just a few seconds, no long-video color drift.

    GitHub · Python · 32 stars · 9 forks · +5 stars in 24 hours · Trending score 1.59

  22. 22
    workingprototype/Fuobe

    The open creative studio on ComfyUI: images, video, 3D and audio on open weights, on your own GPU or the cloud. Camera motions, effects, apps, Cinema, Layers, Image to 3D and an AI agent.

    GitHub · TypeScript · 222 stars · 48 forks · 0 stars in 24 hours · Trending score 1.56

  23. 23
    alinuo666/ComfyUI-Banzhang-All

    ComfyUI custom node pack for MiniMax H3 video generation - three-pass workflow, HD video on a 6 GB GPU. 面向 MiniMax H3 的 ComfyUI 中文插件:三采工作流,6GB 显存也能跑高清视频。

    GitHub · Python · 74 stars · 14 forks · +2 stars in 24 hours · Trending score 1.53

  24. 24
    janishar/h3c-studio

    Local web UI for h3.c — native Metal video/audio generation with MiniMax-H3 on Apple Silicon, no PyTorch or MLX required.

    GitHub · Go · 20 stars · 4 forks · +8 stars in 24 hours · Trending score 1.48