Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
solv3r
Modelsimage to 3d model by jgkwak
jgkwak/solv3r -
AuroraIMG-6M
Modelstext to image model by AuroraAI-Research · pytorch
AuroraAI-Research/AuroraIMG-6M -
Open-MM-RL
Datasets & benchmarksHugging Face dataset by TuringEnterprises
TuringEnterprises/Open-MM-RL -
claude-skill-codex-imagegen
SkillsGenerate, compare, and edit images in Claude Code using your Codex subscription. Background jobs, parallel drafts, and lean context. No image API bill.
git clone https://github.com/JunSeo99/claude-skill-codex-imagegen.git -
Frieren-H3-LoRA
Modelsimage to video model by tazmannner · comfyui
tazmannner/Frieren-H3-LoRA -
MiniMax-H3-DenoMix
Modelsimage text to video model by Deno2026 · diffusion-single-file
Deno2026/MiniMax-H3-DenoMix -
UltraTex
Modelstext to image model by Comfy-Org · diffusion-single-file
Comfy-Org/UltraTex -
mcp-minimax
MCP serversMCP server for MiniMax H3 multimodal video generation
mcp-minimax@2026.11.15.0 -
EdenLive
Modelsimage to video model by VAST-AI · diffusers
VAST-AI/EdenLive -
MMMU
Datasets & benchmarksHugging Face dataset by MMMU
MMMU/MMMU -
codex-slides
Skills🎨 Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. ⚡ 10+ high-quality slides in ~4–5 minutes — Fast mode renders every page in parallel. 🔍 Watch the whole chain live: research → outline → style → render → edit → present → export PDF/PPTX. 🖥️ Browser-first · zero API keys · durable projects.
git clone https://github.com/nexu-io/codex-slides.git -
product-shots
SkillsOpen-source Claude Code skills that turn one product photo into a full set of e-commerce visuals — main images, A+ detail pages, multi-angle shoots, social posts, and ad creatives. For cross-border sellers on Amazon, Shopify, TikTok Shop.
git clone https://github.com/motiful/product-shots.git -
chat-gun
Agents & frameworks🤖 Full-stack AI agent app built with React, TypeScript and LangGraph JS. Streaming, multimodal input, human-in-the-loop, native + MCP tools, Qwen/OpenAI-compatible LLM gateway. Ships an after-sales support agent: cited RAG with abstention, human-approved refunds, idempotent execution. OpenTelemetry + reproducible evals.
git clone https://github.com/HsienW/chat-gun.git -
deepseek-harness-docker
Agents & frameworksCommunity Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI, and headless CLI.
git clone https://github.com/runzhliu/deepseek-harness-docker.git -
Ecommerce product images agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn real product photos and confirmed SKU facts into a matching listing image set with a hero image, feature visuals, lifestyle scenes, size views, and in-box images. 电商上架套图 · 商品主图 · 卖点图
git clone https://github.com/beatra-ai/ecommerce-product-images-skill.git -
gflow-cli
AI repositoriesDrive Google Flow from the command line: Veo video and Imagen images, scripted, batched and pipeline-ready. Ships an MCP server so coding agents can drive it too, giving you and your agents full programmatic control over generation. Unofficial, alpha, not affiliated with Google.
git clone https://github.com/ffroliva/gflow-cli.git -
image to video model by WAS · minimax-h3
WAS/Minimax-h3_Singularity_v2_pruned -
Act as an Algorithm Analysis and Improvement Advisor. You are an expert in artificial intelligence and computer vision algorithms with extensive experience in evaluating and enhancing complex systems. Your task is to…
-
awesome-alternative-uis-for-comfyui
Docs & tutorialsCollection of UIs for ComfyUI
git clone https://github.com/light-and-ray/awesome-alternative-uis-for-comfyui.git -
llmman
AI repositoriesRun any agent on any model, models stored as OCI images
git clone https://github.com/llmmanorg/llmman.git -
build-html-ppt-rpocket-team
PromptsAI가 청중에 맞는 HTML 발표자료와 발표 노트를 만들고 Chromium 기반 시각 검증까지 수행하도록 돕는 스킬·플러그인
git clone https://github.com/NearLegendspirit/build-html-ppt-rpocket-team.git -
iris-z
Modelsdepth estimation model by speridlabs · iris-z
speridlabs/iris-z -
wildjailbreak
Datasets & benchmarksHugging Face dataset by allenai
allenai/wildjailbreak -
Mistral: Saba
ModelsMistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...
mistralai/mistral-saba
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.