Image Generation
Creating, editing and understanding images. As of 2026-11-21, 396 indexed products match this subcategory (100 with full profiles); 187 were published in the last 90 days, against 104 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, ai-engineering-from-scratch leads, holding 36% of the stars of the 320 products here with their own repository. The most common form is MCP servers (88% of indexed products).
SubcategorySegment label: Lagging the catalogue DER
Segment statistics
Whole catalogue (all 396 indexed products, not only profiled ones). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized for its level, with launches growing more slowly than the catalogue’s. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.156, attention is spread as if across about 6 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is moderately concentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 350 | 88.4% | 57 |
| Agent skills | 25 | 6.3% | 25 |
| Plugins | 10 | 2.5% | 8 |
| Agent projects | 4 | 1.0% | 4 |
| Infrastructure | 3 | 0.76% | 3 |
| Frameworks | 2 | 0.51% | 2 |
| Rules packs | 1 | 0.25% | 0 |
| Libraries | 1 | 0.25% | 1 |
3 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Text to ImageGenerating images from prompts. | 77 | 25 | 27 | Lagging the catalogue |
| Image EditingBackground removal, inpainting and upscaling. | 73 | 14 | 46 | Outpacing the catalogue |
| Image UnderstandingDescribing and detecting objects in images. | 43 | 20 | 11 | Lagging the catalogue |
Top 40 products by GitHub stars
Search the directoryProfiled products only (100 of 396), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | ai-engineering-from-scratchLearn AI Engineering! Learn it. Build it. Ship it for others. | Agent project | rohitg00 | 80k | 3d ago | MIT | ||
| 2 | Toonflow-app短剧、漫剧制作工具 Toonflow:开源 AI 视频创作平台,集成剧本创作、智能分镜、角色与场景资产管理、图像生成和视频生成。融合无限画布、AI Agent 与可视化工作流,支持本地部署、自选模型、跨平台客户端、MCP 与插件扩展。Open-source AI short drama and motion comic creation tool with an infinite canvas, AI agents, storyboarding, image and video generation. Self-hosted and extensible, with a canvas-based approach similar to LibTV and TapNow. | Agent project | HBAI-Ltd | 22k | 1d ago | MIT | ||
| 3 | UnstructuredLibrary and hosted platform for partitioning PDFs, Office files, HTML and images into structured elements and chunks for RAG pipelines. | Library | Unstructured | 16k | 2d ago | Apache-2.0 | ||
| 4 | OpenCreatorFormerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc. | Agent skill | krillinai | 14k | 1d ago | Apache-2.0 | ||
| 5 | deeplakeDeeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training. | Infrastructure | activeloopai | 9.3k | 6mo ago | Apache-2.0 | ||
| 6 | codex-ppt-skillGPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents | Agent skill | ningzimu | 8.1k | 5d ago | MIT | ||
| 7 | ODSODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server. | Agent project | Osmantic | 7.9k | 2d ago | Apache-2.0 | ||
| 8 | geo-sleuthAn agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot. | Agent skill | Oldcircle | 7.4k | 2d ago | MIT | ||
| 9 | Remove AI WatermarksIdentify and clean AI watermarks and provenance in your own images, video, audio, and text. | MCP server | wiltodelta | 6.5k | today | Apache-2.0 | ||
| 10 | GPT-Image2-SkillGPT Image 2/2.5/2.6 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing | Agent skill | wuyoscar | 6.2k | 13d ago | MIT | ||
| 11 | locally-uncensoredThe all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. No Docker, no terminal, no cloud required. | Agent project | PurpleDoubleD | 4.5k | 2d ago | AGPL-3.0 | ||
| 12 | skillsGet production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity. | MCP server | scenario-labs | 4.0k | 1d ago | MIT | ||
| 13 | super-agent-party⭐ All-in-one AI companion! Super Agent Party = Self hosted neuro sama + openclaw! ⭐ 全能AI伴侣!超级智能体派对 = 自托管neuro sama + openclaw! | Agent skill | heshengtao | 2.8k | 25d ago | AGPL-3.0 | ||
| 14 | PaperBananaGenerate academic diagrams and statistical plots from text using multi-agent AI. | MCP server | llmsresearch | 2.5k | 2mo ago | MIT | ||
| 15 | bootcampDealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc. | Infrastructure | milvus-io | 2.5k | 1mo ago | Apache-2.0 | ||
| 16 | video-search-and-summarizationNVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs. | MCP server | NVIDIA-AI-Blueprints | 2.0k | today | Apache-2.0 | ||
| 17 | MeiGen-AI-Design-MCPDiscover inspiration and create images and videos with the latest AI models. Works with ChatGPT, Claude, Cursor, and other MCP clients. | MCP server | jau123 | 1.8k | 4d ago | MIT | ||
| 18 | ecom-details-image一个面向workbuddy / Codex 等agent 的跨境电商和国内电商通用视觉创作 Skill。我精选25个高质量案例,涵盖纯色底产品主图、场景化生活图、平铺图、电商详情图、真实场景等等,全部配完整提示词,都可以利用 GPT-Image-2 、Seedream 5.5 API生成最终效果。一键生成电商相关图片!输入产品图片和需求描述,自动生成完整的电商主图、详情页图片、社媒推广图、直播间场景图等全套视觉素材。 与众不同之处是:**Campaign Style Lock** 机制 和 **强推广** 和 **重视转化效果**。 | Agent skill | liangdabiao | 1.8k | 7d ago | — | ||
| 19 | MiniMax-MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs. | MCP server | MiniMax-AI | 1.6k | 11d ago | MIT | ||
| 20 | gpt-image2-ppt-skillsClone any .pptx into your own deck — OpenAI gpt-image-2 mimics the layout, you supply the content. 10 bundled styles. | 把任何 .pptx 模板"抄"成你的 PPT:gpt-image-2 仿版式、你换内容,另含 10 套精选风格。Claude Code / OpenClaw skill. | Agent skill | JuneYaooo | 1.5k | 3mo ago | Apache-2.0 | ||
| 21 | ecommerce-visual-copywriting-skill电商视觉文案设计SOP Skill - 让电商设计小白也能一键做出5年资深设计经验的商品图片.兼容 Claude / Codex / Cursor / Workbuddy 等 SKILL.md Agent. AI-powered e-commerce visual strategy skill for main images, PDP/A+, copywriting, localization, evidence-aware compliance and image prompts. | Agent skill | feichanggege | 1.2k | 22d ago | MIT | ||
| 22 | blender-pluginScenario for Blender: AI images, video, 3D and PBR materials in the viewport, plus a local MCP server for agents. Blender 5.0+ extension, GPL-3.0-or-later. | MCP server | scenario-labs | 1.1k | 1d ago | GPL-3.0 | ||
| 23 | Multi-Agent-Medical-Assistant⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients. | Infrastructure | souvikmajumder26 | 1.0k | 1y ago | Apache-2.0 | ||
| 24 | codex-slides🎨 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. | Agent skill | nexu-io | 987 | 4mo ago | MIT | ||
| 25 | dsh-vision-toolkit[dsh]为纯文本模型设计更强大的视觉工具箱:一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI. | Agent skill | Anionex | 949 | today | MIT | ||
| 26 | comfyui-mcpMCP server + Claude Code plugin for ComfyUI: run workflows, generate images, manage models & VRAM. | MCP server | artokun | 943 | 2d ago | MIT | ||
| 27 | photoshop-mcpMCP server for Adobe Photoshop — 128 tools (generative AI + recipes), standalone web UI. Control Ph… | MCP server | alisaitteke | 930 | 7d ago | MIT | ||
| 28 | OpenCOOD[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V. | Framework | DerrickXuNu | 841 | 2y ago | — | ||
| 29 | context-attachment-managerA local plugin for image-heavy chats in Codex, Claude Code and other AI agents: earlier images become short placeholders instead of going out with every message, the model fetches the original back by its ID (also after compaction), and the prompt cache keeps working. | Plugin | chipfighter | 811 | 1d ago | MIT | ||
| 30 | visual-skillsAI film director skills for agents: cinematic dramaturgy (Murch, blocking, montage) + exact prompt syntax for Seedance 2.5, Kling 3.0 Turbo/Omni, Veo 3.1, Nano Banana 2, GPT Image 2.5. | Agent skill | smixs | 726 | 15d ago | CC-BY-4.0 | ||
| 31 | watch-skillWatch video and live sessions, keep timestamped evidence, and verify an agent's own work. | MCP server | oxbshw | 597 | 5d ago | MIT | ||
| 32 | AAAI-2024-PapersAAAI 2024 Papers: Explore a comprehensive collection of innovative research papers presented at one of the premier artificial intelligence conferences. Seamlessly integrate code implementations for better understanding. ⭐ experience the forefront of progress in artificial intelligence with this repository! | Framework | DmitryRyumin | 589 | 1y ago | MIT | ||
| 33 | draw-uiUI design & mockup skill for Claude Code & Codex, from screenshot to code. 帮你出 UI 设计稿并还原成页面。 | Agent skill | oil-oil | 571 | 1mo ago | — | ||
| 34 | MxPage开源 AI 电商图片工作台:商品主图与详情页、批量图片翻译、小红书图文、LangGraph Agent。支持 Windows / macOS 和本地部署,使用自己的模型 API。Open-source e-commerce image generator, translation & agent workspace. | MCP server | ziguishian | 530 | 21d ago | MIT | ||
| 35 | PPT-Design-SkillPrecision PPT design skill for OpenCode/Claude Code/Codex, with 40,000+ styles, pixel-perfect Build Mode control, AI image generation, and fully editable PPTX. 面向专业演示设计场景,帮助用户从需求分析、视觉方向选择到原生可编辑 PPTX 交付,打造高质量、可持续修改的演示文稿。 | Agent skill | sunchaokun | 511 | 2mo ago | MIT | ||
| 36 | ai-skills24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, TTS, DevOps, and Google Workspace | Agent skill | sanjay3290 | 457 | 19d ago | Apache-2.0 | ||
| 37 | gflow-cliGoogle Flow from any agent: Veo 3.1 and Omni video, Nano Banana and Imagen images, CLI included | MCP server | ffroliva | 432 | today | MIT | ||
| 38 | comfyui-mcp-serverlightweight Python-based MCP (Model Context Protocol) server for local ComfyUI | MCP server | joenorton | 412 | 9mo ago | Apache-2.0 | ||
| 39 | nanobanana-mcp-serverAn MCP server that provides image generation and editing capabilities | MCP server | zhongweili | 411 | 1d ago | MIT | ||
| 40 | cliOfficial Model Studio CLI(阿里云百炼 CLI)built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls. | MCP server | modelstudioai | 371 | 1d ago | Apache-2.0 |
Most common integrations
Third-party services named by products in this node, whole catalogue.
Launches per month
New Image Generation products per monthSRC
Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-12 | 1 |
| 2025-03 | 3 |
| 2025-04 | 1 |
| 2025-05 | 1 |
| 2025-07 | 1 |
| 2025-09 | 7 |
| 2025-12 | 2 |
| 2026-01 | 10 |
| 2026-02 | 10 |
| 2026-03 | 10 |
| 2026-04 | 25 |
| 2026-05 | 22 |
| 2026-06 | 33 |
| 2026-07 | 39 |
| 2026-08 | 41 |
| 2026-09 | 45 |
| 2026-10 | 67 |
| 2026-11 | 62 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
No scored opportunity here
Capability gaps are only scored inside subcategories with at least 20 indexed products, and only the top 80 are kept. None falls under this node.
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .