Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Hotshot-XL
Modelstext to video model by hotshotco · diffusers
hotshotco/Hotshot-XL -
drama-skills
SkillsAI 短剧与漫剧制作 skill 合集:小说改剧本、角色设定三视图、分镜脚本、生图/生视频提示词与成片审片,适配 Claude Code / Codex 等 | Open-source agent skills for AI short dramas & motion comics
git clone https://github.com/zenstory-ai/drama-skills.git -
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 -
Minimax-H3-ComfyUI
Modelsmodel by Alissonerdx · minimax-h3
Alissonerdx/Minimax-H3-ComfyUI -
ai-creator-academy
Agents & frameworksFree, open-source curriculum for making money with generative AI image, video, and audio — for creators and agencies.
git clone https://github.com/Anil-matcha/ai-creator-academy.git -
oil-cover
SkillsVideo cover & thumbnail skill for Claude Code & Codex. 帮你用视频画面做小红书和 B 站封面。
git clone https://github.com/oil-oil/oil-cover.git -
Клод Кот — генерация изображений и видео
MCP serversBest Image and video generation: 20+ models (Kling, Seedance, Veo, NB, FLUX.2), OAuth, pay-per-use.
-
html-explainer
Skills把一个主题做成有配音、字幕、封面的讲解分析类视频 —— 全本地、用 HTML 写画面,稳定音画同步。 面向 AI 编程智能体的确定性 HTML → MP4 渲染流水线。
git clone https://github.com/OneMoh/html-explainer.git -
PinkCherry-NSFW_MiniMax-H3
Modelstext to video model by SexGod1979 · transformers
SexGod1979/PinkCherry-NSFW_MiniMax-H3 -
ByteDance Seed: Seed 1.6
ModelsSeed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.
bytedance-seed/seed-1.6 -
awesome-ai-video-workflows
SkillsAwesome AI product video workflows: turn product images into ecommerce video ads, UGC ads, product launch videos, TikTok, Reels, Shorts, and reusable agent skills.
git clone https://github.com/HiAPIAI/awesome-ai-video-workflows.git -
ChaosIntelligence
Tools & apps把智能体当函数,把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.
git clone https://github.com/Cattmonkey/ChaosIntelligence.git -
image text to text model by DavidAU · transformers
DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored -
daVinci-MagiHuman
Modelsimage to video model by GAIR
GAIR/daVinci-MagiHuman -
gemma-7b
Modelstext generation model by google · transformers
google/gemma-7b -
Qwen3.8-27B-Ultimate
Modelsimage text to text model by DavidAU · transformers
DavidAU/Qwen3.8-27B-Ultimate -
cevahir-ai
AI repositoriesCevahir Zihin: a mind that learns by living, not a Transformer. It keeps knowledge as evidence on ties, attends with a Seven-Place Focus and learns from every conversation. Also: a Turkish BPE tokenizer, a Transformer language-model core and cognitive systems.
git clone https://github.com/myylogic/cevahir-ai.git -
airllm
AI repositoriesAirLLM 2.8T LLM inference with single 4GB GPU
git clone https://github.com/lyogavin/airllm.git -
claude-remotion-skill
SkillsOpen-source Claude agent skill that teaches Claude Code, Claude Desktop & Claude AI to create and edit professional motion graphics videos with Remotion. AI video editing, B-roll, captions, sound design — from one prompt.
git clone https://github.com/haidrrrry/claude-remotion-skill.git -
text to video model by FastVideo · diffusers
FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree -
phi-2
Modelstext generation model by microsoft · transformers
microsoft/phi-2 -
Andy-Video-Skill
SkillsClaude Code 视频生成 Skills 精选目录:Manim、React Video、录屏转视频等|Curated catalog of 12 video-generation Skills for Claude Code — Manim, React Video, Screencast-to-Viral, and more.
git clone https://github.com/AIPMAndy/Andy-Video-Skill.git -
LTX-2.3-GGUF
Modelsimage to video model by unsloth · ggml
unsloth/LTX-2.3-GGUF -
smol-training-playbook
Tools & appsHugging Face space by HuggingFaceTB
HuggingFaceTB/smol-training-playbook
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.