Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
video to video model by akatz-ai · diffusion-single-file
akatz-ai/MiniMax-H3-Person-Remover-LoRA -
image to video model by taobao-content-ai · minimax-h3
taobao-content-ai/MiniMax-H3-PTD-RefAsymOPD-LoRAs -
sglang
AI repositoriesSGLang is a high-performance serving framework for large language models and multimodal models.
git clone https://github.com/sgl-project/sglang.git -
Open-H3-Regenerate-2K
Modelsvideo to video model by Efficient-Large-Model · minimax-h3
Efficient-Large-Model/Open-H3-Regenerate-2K -
minimax-h3-image-restyle
Modelsimage to image model by witcherderivia
witcherderivia/minimax-h3-image-restyle -
project-maya
AI repositoriesProject 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.
git clone https://github.com/mw00/project-maya.git -
MiniMax-H3-Director-Cut-Studio
PromptsPremiere-inspired PySide6 director studio for MiniMax H3 Ref2VA with AI shot planning, semantic media enrichment, timeline prompt reconciliation and shot-aware long-video rendering through ComfyUI.
git clone https://github.com/karuvanan/MiniMax-H3-Director-Cut-Studio.git -
H3-Dials
Modelsmodel by MATLOWAI · minimax-h3
MATLOWAI/H3-Dials -
H3_Ripple
Modelsvideo to video model by WepeNerd · minimax-h3
WepeNerd/H3_Ripple -
awesome-minimax-h3-skills
SkillsMiniMax H3 官方 Skills 的可视化发现与参考站点 · A visual discovery & reference index for the official MiniMax H3 Skills (independent community project)
git clone https://github.com/gordonlu/awesome-minimax-h3-skills.git -
infinite-creation
Skillsinfinite-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。
git clone https://github.com/SwotAtmk/infinite-creation.git -
FastH3-Omni-Comfy
Modelsmodel by FastVideo · diffusion-single-file
FastVideo/FastH3-Omni-Comfy -
tokenspeed
AI repositoriesTokenSpeed is a speed-of-light LLM inference engine.
git clone https://github.com/lightseekorg/tokenspeed.git -
Open-H3-Regenerate-2K-IC
Modelsvideo to video model by Efficient-Large-Model · minimax-h3
Efficient-Large-Model/Open-H3-Regenerate-2K-IC -
Pika-H3-Flex-Turbo-LoRA
Modelsimage to video model by Pika-Labs · minimax-h3
Pika-Labs/Pika-H3-Flex-Turbo-LoRA -
Feranor Resilience
MCP serversScan/purge hidden text & score web domains: TLS, DNS, headers, speed. Free scans, $0.01 actions.
-
AMNT SVG
MCP serversText or image to clean, editable SVG from $0.01. Free SVG library + agent search, no key.
-
TensorSharp
AI repositoriesA native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, iPhone App, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/iOS/Linux with full GPU capability
git clone https://github.com/zhongkaifu/TensorSharp.git -
# ============================================================ # Prompt Name: Project Skill & Resource Interviewer # Version: 0.6 # Author: Scott M # Last Modified: 2026-01-16 # # Goal: # Assist users with project…
-
Pika-H3-Flex-Turbo-LoRA
Modelsimage to video model by akhaliq · minimax-h3
akhaliq/Pika-H3-Flex-Turbo-LoRA -
Reclypse Utility Node
MCP serversFive text and JSON utilities. Paid execution: 0.01 USDC standard or 0.05 USDC priority on Base.
-
talking-avatar-video-skill
SkillsTalking avatar video agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn one portrait and a script or voice track into an AI presenter video for explainers, lessons, and product messages. 数字人口播视频 · 照片说话
git clone https://github.com/beatra-ai/talking-avatar-video-skill.git -
codex-mobile
AI repositories🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀
git clone https://github.com/friuns2/codex-mobile.git -
mcp-minimax
MCP serversMCP server for MiniMax H3 multimodal video generation
mcp-minimax@2026.11.15.0
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.