The best Image Generation Skills for Claude Code in 2026 depends on the visual style you want (259 of 265 rated SAFE on Agent Skills Hub): We had 130 image skills make the same six pictures on the newest models. Claude Code with no skill got every line of text right, 66 skills matched it and none did better, so install one for its look: the 7 below each have one of their own and still kept every rule of the brief. See the test →
Image generation skills and MCP servers for Claude Code, Codex and other agents, security-graded: GPT Image, Nano Banana, Flux, image editing and design assets. Vet before you install.
An image generation skill is an installable package (a folder with a SKILL.md file, or an MCP server) that lets a coding agent such as Claude Code or Codex call an image model, such as Google's Nano Banana (Gemini), FLUX or GPT Image, to create or edit pictures and save them into your project. The skill supplies the connection to the model and the know-how for prompting it. Most bill you through your own account or API key with the model's provider; ComfyUI-based ones can run open models on your own machine instead.
Each model drew the test's poster once, with no skill, through the same provider; the text was read by OCR and checked by hand. One picture each, and a second try can differ: Nano Banana 2.1 misspelt a Chinese line in an earlier try. The skill test on this page sent every image call to GPT Image 2.6, Nano Banana 2.1 or FLUX 3.
For a one-colour print look. Every picture came out in blue halftone on cream with oversized type, like a risograph poster, and every rule of the brief held. It drew 28 times to get there, the most of any skill that followed the brief (10.8 minutes, $0.17).
For warm, hand-drawn illustration. It drew the mascot in a cartoon line style and put it on the poster and the bag too, so the six read as one set (9.5 minutes, $0.09).
For a voxel (3D pixel-block) look. The loaf, the mascot and even the bag came out as clean voxel art on white, with the text set plainly below (4.7 minutes, $0.07).
For flat vector graphics. Built for research-paper figures, it drew a sun-and-loaf poster in clean shapes and a line-drawn mascot, closer to an infographic than a photo (7.8 minutes, $0.05).
For posters built on Chinese lettering. It set a giant calligraphic 晨 (morning) behind the loaf; its mascot and bag stay close to the default photo look (3.6 minutes, $0.05).
For little isometric scenes. Built to turn photos into paper miniatures, from the brief alone it stood the mascot in a tiny bakery stall, with props from the same scene on the poster and the bag (4.6 minutes, $0.10).
For a quiet, minimal look. Built to turn your photos into airy hand-drawn pictures, from the brief alone it drew small subjects in a lot of white space with light type, the opposite of the busy default (6.7 minutes, $0.05).
From our 2026-11-08 test of 130 skills: each of these made all six pictures, wrote every line of text right, kept the formats asked for, added no text and drew one consistent mascot, and its set looks different from what Claude Code made with no skill (top). Not ranked; every result is in the test section below.
On 7 and 8 November 2026 we had 130 image generation skills make the same six pictures in a throwaway sandbox, driven by Claude Code (Claude Opus 5.5): a 3:4 poster for a made-up bakery with six exact lines of English and Chinese text, a square photo of a kraft-paper bag printed with the shop's name, and four square pictures of one mascot in four poses. Every image call went to the newest model of the family the skill asked for (GPT Image 2.6, Nano Banana 2.1 or FLUX 3) through one provider, so the skills compare on their prompts and workflow, not on the model they default to. Claude Code with no skill made the set too. The text was read by OCR, and by hand where OCR stumbled; the formats were measured; a vision model judged whether the four mascots are one character; the look was judged by eye. Each skill ran once, with 20 minutes.
What we found: On the newest models the text is not where skills differ. Claude Code with no skill wrote all six lines and the bag's name correctly, in 5.1 minutes for $0.07 of image calls. 66 skills did as well and none did better. 30 more made all six pictures but broke a rule, most often the format (26 drew the poster square, landscape or 2:3, or the square pictures some other shape) or text on the mascots (8). 31 made no picture: 20 work only with their own service or account, 7 do another job, 2 wait for a person and 2 drew nothing in 20 minutes. By eye, 77 of the 96 complete sets look close to the no-skill set and 19 have a look of their own. See the six Claude Code made with no skill →
Image Generation Skills for Claude Code are AI-powered software designed to help developers and teams tackle image generation-related tasks more efficiently. These tools are typically published as open-source projects on GitHub and can be integrated into existing workflows via MCP (Model Context Protocol), Claude Skills, or standalone agent frameworks. On Agent Skills Hub, we index 265 quality-scored Image Generation Skills for Claude Code across languages including Python, JavaScript, TypeScript.
In 2026, the AI agent ecosystem is maturing rapidly. Image Generation Skills for Claude Code can significantly boost development efficiency by automating repetitive tasks, reducing human error, and providing intelligent suggestions. The top 3 tools — ian-xiaohei-illustrations, ip-as-logo-skill, mono-color-skill — have earned an average of 7,743 GitHub stars. 194 of the listed tools come with clear open-source licenses, ensuring freedom to use and modify.
When choosing among Image Generation Skills for Claude Code, consider these factors: 1) Community activity — GitHub stars and recent commit frequency indicate reliability; 2) Integration method — check if it supports MCP, Claude, or your preferred agent framework; 3) Language compatibility — the most common language in this list is Python; 4) Quality score — Agent Skills Hub's 9-dimension quality score rates documentation completeness, structure and agent readiness, not the code. Our recommendation: start with ian-xiaohei-illustrations — it has the most GitHub stars on this list.
Codex Skill for generating illustrations for Chinese “Little Black Grotesque” body text, hand-drawn on white 16:9 backgrounds with sparse red, orange, and blue…
git clone https://github.com/helloianneo/ian-xiaohei-illustrations.git
A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos.
npx skills@latest add s1dashu/ip-as-logo-skill
One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained typography.
Get 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.
npx skills add scenario-labs/skills --skill "*"
Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
pip install paperbanana
Discover inspiration and create images and videos with the latest AI models. Works with ChatGPT, Claude, Cursor, and other MCP clients.
/plugin marketplace add jau123/MeiGen-AI-Design-MCP
A modular Codex Skill for directing and expanding detailed AI female portrait prompts.
npx skills@latest add liyue-aigc/female-portrait-director -g -a codex -y
A skill for workbuddy/Codex agents: generates e-commerce product, detail, social, livestream images from photos and descriptions via GPT-Image-2 API.
git clone https://github.com/liangdabiao/ecom-details-image.git
Guizang’s material illustration skill: creates annotated images, improves charts, and makes reference illustrations.
npx skills add https://github.com/op7418/guizang-material-illustration --skill guizang-material-illustration
AI image generation skill for Claude Code - Creative Director powered by Gemini
/plugin marketplace add AgriciDaniel/banana-claude
GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents
GPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
/plugin marketplace add wuyoscar/gpt_image_2_skill
NanoBanana PPT Skills uses AI to generate PPT images and videos, with smart transitions and interactive playback.
git clone https://github.com/op7418/NanoBanana-PPT-Skills.git
Claude Code skill: turns content into copyable image prompts using 5 built-in hand-drawn styles: coloring, line art, crayon, Ghibli, bean-person doodles.
git clone https://github.com/threerocks/hand-drawn-styles.git
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Chinese hand-drawn technical PPT full-page image generation skill, with 21:9 covers, 16:9 content images, and PNG output
git clone https://github.com/helloianneo/ian-handdrawn-ppt.git
Clone 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.
AI Image Prompts — 10,000+ curated prompts for any model. Works with Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E, Flux, Stable Diffusion, and more.
npx skills i YouMind-OpenLab/ai-image-prompts-skill
Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
claude plugin install comfyui-mcp
Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.
npm install -g ima2-gen
A source-available Codex skill for distilling photographs into sparse editorial abstractions.
git clone https://github.com/Evianis/travel-photo-abstraction.git
本地优先的多模型 AI 图片生成工作台,支持 GPT Image、Gemini、图像编辑、素材库、模板与并发任务。Local-first AI image workbench for GPT Image & Gemini, with editing, reusable assets, templates and task history.
git clone https://github.com/kadevin/ilab-conjure.git
AI 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.
git clone https://github.com/smixs/visual-skills.git
Codex skill for turning everyday photos into poetic white-paper hand-drawn illustrations.
Claude Code skill: generate UI design mockups with GPT Image 2 via ZenMux
npx skills add oil-oil/draw-ui
Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images
git clone https://github.com/helloianneo/ian-xiaohei-scenes.git
TaiT-CRT-Interface-Skill is a Codex image generation skill that transforms user-uploaded portraits, photographs, or text descriptions into a retro illustration with the feel of an early CRT computer interface.
🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古建筑与在地文化照片 → 艺术指导海报
npx skills add https://github.com/op7418/guizang-yingzao-skill --skill yingzao
19 Claude Code skills for Higgsfield AI — automate image generation, Seedance 2.0 video creation, and full UGC ad pipelines with Playwright browser automation
E-commerce product image generator skill — 39 scenario templates, GPT-Image-2/2.5 (Flare/Sunburst) model routing, campaign consistency lock, platform compliance. 电商做图 Skill:39 场景模板×双模型路由×套图一致性×平台合规。
git clone https://github.com/buluslan/gpt-image2-ecommerce.git ~/.claude/skills/ecom-image2
A universal skill for generating realistic images
Edit photos by describing the change, on your own GPU. A free, open-source alternative to Nano Banana and ChatGPT image editing: photos stay on your computer, no daily limit. One installer for Windows, Mac and Linux sets up the best open model (Qwen-Image 2.1). MCP server for AI agents.
claude mcp add --scope user kokon -- "$env:LOCALAPPDATA\Kokon\kokon-mcp.exe"
Agent-friendly ComfyUI workflow skills for OpenClaw, Hermes Agent, Codex, and Claude Code; complementary to Comfy official local MCP.
git clone https://github.com/HuangYuChuh/ComfyUI_Skills_OpenClaw.git comfyui-skill-openclaw
Use your ChatGPT subscription to generate images from the command line — no OPENAI_API_KEY, no gateway, no daemon. Zero-dep Python CLI + AI-agent skill.
npx skills add leeguooooo/image-use -g
illo skill — an AI agent skill that turns ideas and articles into original print-style editorial illustrations, starring a recurring mascot. 30+ characters packs, with ability to create your own.
npx skills add tmchow/illo-skill --skill illo
AI image generation CLI powered by Gemini 3 Pro. Green screen transparency, reference images, style transfer. Also a Claude Code plugin.
git clone https://github.com/kingbootoshi/nano-banana-2-skill.git ~/tools/nano-banana-2
lightweight Python-based MCP (Model Context Protocol) server for local ComfyUI
git clone https://github.com/joenorton/comfyui-mcp-server.git
AI image generation MCP server powered by Google Gemini, with smart model selection and 4K output
uvx nanobanana-mcp-server@latest
A Claude Code skill to generate images with Nano Banana
git clone https://github.com/kkoppenhaver/cc-nano-banana ~/.claude/skills/nano-banana
Local MCP server for ComfyUI — run your local ComfyUI from AI agents
pip install comfy-mcp "comfy-cli>=1.14.0" # this server + the engine it wraps
MCP server wrapping 米醋 gpt-image-2 / gpt-image-2-pro proxy. One-click install for Claude Code / Codex / Cursor.
git clone https://github.com/Subaru486desuwa/micu-image-mcp.git
Claude Code skill that compiles vague requests into complete gpt-image-2 prompts: no negative prompts, result-based descriptions, validation scripts, C1–C10
git clone https://github.com/gongnyang/gongnyang-prompt-kit
Agent skill from Y Build for turning AI images and videos into playable game art assets
npx skills add ybuild-ai/ai-game-art-pipeline-skill --skill ai-game-art-pipeline -g
Open-source skill and IP character library for illustrating Chinese long-form articles with recurring characters, cognitive anchors, improvised metaphors, and…
git clone https://github.com/xiaohuailabs/xiaohu-ip-studio ~/.claude/skills/xiaohu-ip-studio
Local cockpit for Codex imagegen, pixel art, image editing, animation, and sprite-sheet workflows.
Create high-fidelity Codex companions from 2+ photos with local open-weight neural editing and no OpenAI API key.
Zero-skill cinema. Senior-director prompts on autopilot. A Claude Code Skill for high-quality AI image / video / music prompt crafting and browser-based execution across 14+ generative platforms.
⚡ CLI toolkit for Google Flow — Nano Banana Pro images, Omni Flash videos, MCP v2 & OpenAI API.
git clone https://github.com/kodelyx/flow-agent.git
Claude Code/Agent Skill for making App Store Screenshot generator with GPT Image 2. Give it your App Store link & screenshots of your app and it will produce beautiful app store screenshots ready to upload to Apple (or Google)
npx skills add hypersocialinc/shots
MiniMax-H3-Image, an open-weight model for 16-megapixel image generation and editing.
npx skills add https://github.com/MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing
Image generation (gpt-image-2) and GPT-5 subagents for Claude Code — through the Codex CLI login you already have. No OpenAI API key.
/plugin marketplace add Sateezg/codex-bridge
Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.
A Nano Banana MCP server, which you can integrate to cursor/claude code and any mcp client
npx nano-banana-mcp
MCP server + embedded terminal that lets Claude Code see and edit your ComfyUI workflows
Custom node for ComfyUI/Stable Diffustion
git clone https://github.com/glibsonoran/Plush-for-ComfyUI.git.
Codex Chinese-content interactive image generation system skill: cognitive-anchor image breakdown, 49 content styles, 8 logo/icon modes, covers, visuals, and b…
git clone https://github.com/izscc/cc2image.git ~/.agents/skills/zscc配图生成器
Xiaohongshu post generator based on gpt-image-2, with natural-language editing.
git clone https://github.com/JuneYaooo/xhs-writer-skill.git
MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Supports Nano Banana (Gemini), OpenAI GPT Image, and BytePlus Seedream.
npx mcp-image skills install --path <target-directory>
Design Buddy: visual production Agent Skills for brand design systems, GPT-image-2 images, diagrams, infographics, logos, slide decks, WeChat layouts and social images
npx skills add SpaceZephyr/design-buddy
Experimental bilingual Codex skill for ETERNA-inspired image2image cinematic color and composition.
Python & Node package to use GPT image 2.0 model via codex subscription
npm install -g god-tibo-imagen
A full-process toolkit for AI Agent AIGC comic video creation.
npm install -g workrally
47 installable visual-design skills for Codex, with reusable Python tooling and versioned packages. Turn photos into artwork. Try online: style.abdc.online
Generate GPT images from Codex or Claude Code using a ChatGPT subscription, without the Images API.
Free, open-source desktop editor for AI inpainting: select, prompt, get a colour-matched layer. FLUX 3 Image, FLUX.2, GPT Image, Nano Banana, Seedream and Qwen through your API key or your own ComfyUI. Layers, PSD export, MCP.
AI image/video workbench: Agent/workbench modes, infinite canvas, assets, prompt reverse search/plaza, PWA, external config, Grok, GPT Image 2, mobile.
git clone https://github.com/doudou770/flyreq-image-studio.git
Infinite canvas plugin for codex; Codex无限画布插件,图层分离,涂抹修改
Please install Codex-Canvas according to https://github.com/Xiangyu-CAS/codex-canvas.git and its INSTALL.md.
After installation, tell the user to start a new Codex task and type `@Codex-Canvas open the codex canvas`.
12 电商出图 Agent Skills for Claude Code / Codex / Cursor · GPT Image 2.5 (Flare/Sunburst) · Amazon 白底主图, A+, 场景图, 模特图, 小红书封面, 淘宝详情页
npx skills add xianyu110/ecommerce-image-skills
A skill for generating images in Codex
git clone https://github.com/fengfengzhidao/codex-image2-skill.git
GPT Image 2 Skill / CLI / Web / Desktop
cargo install gpt-image-2-skill --locked
让任何 Agent 调用 Codex 内置生图(MCP + CLI + Skill),内置小红书、视频封面、Mondo 海报技巧 · Codex image generation for any agent
npx skills add joeseesun/qiaomu-codex-imagegen
AI Tool Use API for Anima anime/illustration image generation. Supports MCP Server, HTTP API, and CLI.
git clone https://github.com/Moeblack/ComfyUI-AnimaTool.git
Official agent skills from Black Forest Labs for FLUX image and video generation — prompting guides and API integration patterns for Claude Code, Codex, and any agentskills.io-compatible agent.
npx skills add black-forest-labs/skills
Codex/OpenClaw skill for generating images with ChatGPT/Codex OAuth
Zero-GPU-idle gateway for running ComfyUI on ephemeral Google Colab VMs with Zero-Trust Access
A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)
uv tool install git+https://github.com/iconben/z-image-studio.git
Turn photos into source-faithful editorial artworks with an Agent Skill — adaptive layouts, controlled abstraction, and a Strict Fidelity composition path.
Eastern culture editorial poster v2 Codex skill: Image 2 generation, concise Chinese titles, authentic cultural artifacts, A/B/C triptych testing
OpenCode plugin: image generation via your ChatGPT subscription
FANTASY-qiqiguaiguai Codex skill for funny editorial social posts, 3:4 posters, collage, street snapshots, pets, travel and Chinese typography.
Natural language → ComfyUI workflow JSON. 34 built-in templates, 360+ node definitions, auto model download. Supports txt2img, img2img, txt2vid, img2vid, audio, 3D generation across SD1.5/SDXL/SD3/FLUX/Wan2.2/HunyuanVideo/LTXV/Mochi/Cosmos + LLM integration. Works as a skill for Claude Code, Cursor, and other AI coding agents.
git clone https://github.com/twwch/comfyui-workflow-skill.git ~/codes/comfyui-workflow-skill
One ComfyUI skill for every AI coding agent (Claude Code, Codex, Gemini CLI, Qwen Code): drives a local ComfyUI end to end. 75 model prompt recipes, 581 templates, plus standalone Seedance, Krea and MiniMax H3 skills. Hardware-aware selection, workflow building, multi-shot video, ControlNet, HDR. By Chronicle of Brothers.
git clone https://github.com/SlavaSexton/ComfyUI-Agent-Kit.git
Native-feeling image generation for Claude Code, powered by your local Codex (ChatGPT) image_gen. No API key needed.
/plugin marketplace add actionow-ai/c2c_img
Skill for popular science image content creation on Xiaohongshu
git clone https://github.com/NimaChu/xhs-imagen.git
Enable agents to run registered ComfyUI workflows through a local ComfyUI server using this repo’s CLI, returning structured JSON outputs.
pipx install comfyui-agent-skill-mie
A recipe-driven WaaS platform for ComfyUI that turns complex workflows (Image, Audio, Video, 3D) into intuitive Gradio UIs, high-level semantic APIs, and MCP tools for LLMs & AI Agents.
Connect Claude to image generation with Agent Skills. Three levels: a zero-cost code-based design engine, a Three.js 3D renderer, and a real diffusion model on Cloudflare. Plus an AI Storybook pipeline that turns a plain-English story into an illustrated, narrated HTML book.
19 visual-style skills for gpt-image-2 that turn articles, topics, products, or existing visual assets into complete prompts.
Codex skill for API-based image generation through OpenAI-compatible providers
Subject-aware minimal-zine image production for Agent Skills: art direction, generation, series, evidence, and real-bitmap QA.
npx skills add jiahuiqu17/paper-signal
Codex plugin for cross-border ecommerce images: 8 workflows, GPT Image 2 prompt optimization, approval, per-image checks, and resumable runs.
Create explanatory diagrams and transparent character illustrations in a consistent comic ink-line style for concepts, processes, comparisons, and articles.
npx skills add oil-oil/oil-visual
MCP for Replicate Flux Model - A powerful tool for generating customized images and SVG assets that match specific coding vibes and aesthetic styles. Streamline your visual asset creation process with AI-powered design generation tailored for developers.
git clone https://github.com/awkoy/replicate-flux-mcp.git
Voxel Icon — 30 free PNG icons plus a self-contained Codex skill for low-density isometric voxel art
npx skills add BIAsia/voxel-icon
Local-first MCP server for the Higgsfield AI API: 85 typed image & video models (Seedance 2.5, Kling 3.0, Wan 3, Genjutsu, Soul, Cinema Studio), webhooks, cost estimates, Soul ID training. Opt-in web backend for Sora 2, Veo 3, Nano Banana.
uvx --from higgsfield-mcp-unified higgsfield-mcp # starts the stdio MCP server
Open-source ai image generator skill and ai video generator skill for Codex, Claude Code, OpenClaw, Cursor, and more. Powered by CyberBara API with Nano Banana, Sora 2, Seedance, and Kling support. No need to master prompt, this skill optimize your prompt for all kinds of creations like slides, anime and much more.
npx skills add ZeroLu/Ultimate-AI-Media-Generator-Skill --list
Codex skill that turns one image or text concept into a WeChat-ready Chinese sticker pack people will actually send. Sendability-gated, 4-keypose → 16-frame, no model-drawn text.
git clone https://github.com/lisamsung/agent-meme-forge.git
Xiaohongshu skill that generates cover images from user-defined topics using the Nano Banana Pro image-generation model.
A Codex plugin and local MCP runtime for context-bounded image generation and inspection.
A collection of Agent Skills by Cali Castle.
npx skills add CaliCastle/skills --skill signal-geometry
Session-scoped Claude Code agent for ComfyUI video production — 12 specialized skills for image gen, video, voice cloning, LoRA training, and publishing
git clone https://github.com/MCKRUZ/ComfyUI-Expert.git
A muted, poetic paper-poster Agent Skill for low-saturation zine-style image generation.
教 Claude Code/Codex 真正用好 gpt-image-2 的 skill 包 · Drop-in skill teaching agents to actually use GPT Image 2 — intent-first prompting, surgical edits, parallel batching, visual self-verification
git clone https://github.com/jiangmuran/claude-image.git
Scientific figure workbench with independent VLM/image connections, Chinese UI, and unified size controls.
uvx paperbanana-cn studio
AI visual director for turning personal photos into structured, editable visual narratives.
git clone https://github.com/swping999/scene-card-studio.git
Custom nodes for ComfyUI — video effects, batch processing, prompt tools, image manipulation & automation utilities
git clone https://github.com/MushroomFleet/DJZ-Nodes
AI-powered image generation using Google Gemini or OpenAI (gpt-image-2), integrated with Claude Code via Skills or Claude.ai via MCP (Model Context Protocol).
/plugin marketplace add guinacio/claude-image-gen
A Claude Code skill that transforms any content or Mermaid diagram into stunning visual explanations — whiteboard sketches, infographics, mind maps, and more — powered by OpenAI or Gemini image generation.
A TypeScript implementation of a Model Context Protocol (MCP) server that integrates with PiAPI's API. PiAPI makes user able to generate media content with Midjourney/Flux/Kling/LumaLabs/Udio/Chrip/Trellis directly from Claude or any other MCP-compatible apps.
npx -y @smithery/cli install piapi-mcp-server --client claude
Claude Code skills for Bria AI - generate, edit, and transform images with Fibo, RMBG-2.0, and VGL structured prompts
npx skills add bria-ai/bria-skill
Turn a prompt into polished, full-slide PPT decks with gpt-image-2. 把一句提示词转换成由 gpt-image-2 生成的、精美完整的整页式 PPT 演示文稿。
git clone https://github.com/stevenjinlong/awesome-ppt-skills.git
GPT Image 2 (ChatGPT Images 2.0) skill for Claude Code — best-in-class typography, two endpoints (T2I + edit), Fal AI integration, structured-JSON prompting patterns
echo "FAL_KEY=your-fal-ai-key" >> .env
New nANO-Banana Google Gemini API for ComfyUI generate images, transcribe audio, sumarize videos. Making a separate implemetation of my old IF_AI tools for easy installation
git clone https://github.com/if-ai/ComfyUI-IF_Gemini
Turn photographs into quiet source-colour isometric paper miniatures with four combinable output modes.
git clone https://github.com/nevertoday/xxd-panel-028.git
Nano Banana Pro Skills
OpenClaw/Claude Code SKILL.md for gpt-image-2 via Codex OAuth, no OPENAI_API_KEY required
An MCP server that integrates with gpt-image-1 & Gemini imagen4 model for text-to-image generation services
Translate Chinese regional culture into restrained contemporary large-type and editorial posters, not tourism promotion.
git clone https://github.com/dacnay816y62-hub/regional-culture-poster.git ~/.agents/skills/regional-culture-poster
MCP server for Google Gemini — free image generation, editing & chat via browser cookies. No API keys needed.
git clone https://github.com/AndyShaman/gemini-webapi-mcp.git
Claude Code skill for AI image generation via Codex CLI OAuth (gpt-image-2) / Codex CLI OAuth를 통한 AI 이미지 생성 Claude Code 스킬
git clone https://github.com/wjb127/codex-image.git ~/.claude/skills/codex-image
Self-hosted AI studio for images, video and music on your own GPU. Multi-user with logins and limits, no node graphs, drivable over MCP.
git clone https://github.com/PotionUI/PotionUI.git potionui && cd potionui
Standalone Skill and Codex Plugin for OpenAI-compatible image generation, editing, batch workflows, QA, and focused canvas editing.
Nano Banana App Store Screenshot Skill
npx skills add chawlaaditya/NanoBananaASO
CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, REST/SSE, and MCP.
GPT Image 2 AI image generation skill for OpenClaw, Claude Code, OpenCode, and Cursor - one command install
RunAPI MCP server for model discovery, pricing lookup, media task creation, and balance checks.
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
A high-quality GPT-Image-2 prompting skill with bilingual README, structured prompting methods, templates, and examples.
Z-Image Skill - AI Image Generation for Claude Code | 用自然语言生成 AI 图片的 Claude Code 技能
Install zimage-skill from https://github.com/yizhiyanhua-ai/zimage-skill
AI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with EU AI Act content marking.
npx -y mediagen mark ./output/hero.jpg --visible-label
Awesome skills for AI image generation, video generation, song generation and more!
Claude Code plugin that exposes Codex CLI's built-in imagegen skill as /codex-image:* user-invoked slash commands.
Agnes AI skill for text, image, and video APIs with persistent auth and OpenAI-style workflows
Turn reference images into pixel-art game assets,for indie game developers.
Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.
Codex skill with game-inspired and crochet style templates, plus 2D, 360° panorama, spatial-depth, colored point-cloud, and video workflows.
Agent Skill for creating BioRender-inspired, publication-quality biomedical mechanism figure prompts for GPT Image, Codex, Claude Code, and OpenCode.
A policy-aware Codex skill that turns product photos into platform-adapted e-commerce detail pages with modular image generation, deterministic typography, slicing, manifests, and validation.
Claude Code Skill: AIGC 科研绘图 4 步工作流(GPT-image-2 × Gemini Vision × Nano Banana 2 × draw.io)— 把顶会论文配图从半天压缩到 10 分钟,产出可编辑 .drawio/.pptx/.svg
灵感绘.skill: A tested library of GPT-Image2 image prompt examples covering 13 categories, for AI image ideas and creative reference.
skill to create custom icons using IDEs or extentions that have image generation support
Skill for image-style replication and generation with structured JSON prompts, not long prose, for Nano Banana and GPT-Image; apiz-cli generates, runtime agent…
MCP server for Google Antigravity image generation
ChatGPT image generation/editing: OpenAI-compatible API, studio, account pools, signup, logs/images, Docker self-hosting, gpt-image-2/codex-gpt-image-2.
MCP server for OpenAI Image Generation & Editing — text-to-image, image-to-image (with mask), no extra plugins.
Scientific paper figure generation Skill for agents: web research-figure conventions, controlled colour, topology planning, and image generation. 科研论文图生成 Skill:联网参考、配色与拓扑规划。
MCP server for AI image generation and editing using Google's Gemini Flash models. Create images from text prompts with intelligent filename generation and strict text exclusion. Supports text-to-image generation with future expansion to image editing capabilities.
Codex skill for director-level Eastern beauty AI image prompts, covering gu feng, Eastern fantasy, modern Chinese aesthetics, SweetHomeGirl lifestyle portraits, prompt routing, style systems, and image-generation-ready prompts.
一张照片生成 AI 数字人口播:本地 ComfyUI 全流程(Qwen3-TTS 克隆声音 + MiniMax H3 对口型 + Qwen Image + Music 3),不花积分;5 种剪辑风格 + 48 个博主级包装组件。AI digital-human talking-head videos from one photo, generated locally with ComfyUI (Qwen3-TTS + MiniMax H3 lip sync), no credits. Agent skill for Claude Code / Codex / OpenClaw / WorkBuddy …
Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
Context-aware image generation skill for Claude Code — analyzes website brand identity and generates on-brand images via Gemini MCP
Codex skill for OpenAI Images API generation and editing in API key mode
Generates on-brand marketing imagery (ad creatives, logos, slides, carousels) from a brand DESIGN.md via gpt-image-2 — a Codex / Claude Code skill.
Gemini Vision & Image Generation MCP for Claude Desktop and Claude Code
Send a product photo; this skill uses GPT-Image 2.5 to generate frames and a looping product GIF in one call. No design or technical skills needed.
Claude Code skill for AI image generation using Nano Banana Pro
GPT-image-2 prompt engineering methods: use real reference names instead of adjectives, default to short Chinese prompts. Includes single-image, batch-grid, an…
AI Claude Code Skill: GPT-Image-2, Foundry, Gemini Game Development Pixel Art, Sprite & Tilemap Image Generation
Codex-only AI visual material production skill — slides + WeChat covers + Bilibili/YouTube thumbnails, powered by built-in image_gen (no API fees)
GPT Image 2.5 Sunburst & Flare toolkit for agents: generation, reference and masked edits, PNG/JPEG/WebP, dry-runs and validated receipts. Experimental ChatGPT/Codex backend.
🎨 自媒体 IP 配图生成器 — 10种画风 × 双版本输出 × 中文提示词 | Cola/Claude Skill for IP image generation with Dreamina
适用于自定义 OpenAI 兼容 base_url 的 Codex 独立生图 skill,支持文生图与参考图编辑,并可自动从本地 Codex 配置中读取 URL 和 API Key。 An independent Codex image-generation skill for custom OpenAI-compatible base_url setups, supporting text-to-image and reference-image editing while automatically loading the endpoint URL and API key from the local Codex configuration.
Generate, compare, and edit images in Claude Code using your Codex subscription. Background jobs, parallel drafts, and lean context. No image API bill.
Claude Code skill for generating and editing images with OpenAI's gpt-image-2
CS system (CortexOS) MCP — one agent service that strings a personal open-source toolchain together: image generation, local vision, contrast gating, Markdown typesetting. Capability groups: a group's tools appear only when its CLI is installed.
Official FLUX MCP server. Generate, edit, vary, and browse FLUX images from any MCP client.
680个AI-HIVE Agent Skills:新增340个AI大模型专家中文技能,覆盖Seedance、Nano Banana、GPT Image 2、Seedream、MiniMax、电商图片视频、广告营销与AIGC工作流。
A Model Context Protocol (MCP) server for generating and editing images using the OpenAI gpt-image-1 model.
Codex skills for scientific infographics, research cover visuals, and publication-grade paper figures using ChatGPT image generation.
MCP server for Gemini 3 Nano Banana Pro image generation
NexcoreVision OCR + CNN + VLM evidence architecture, consent-gated local ComfyUI/Qwen deployment, and Agnes media generation in one Agent Skill.
Use Codex + GPT Image 2 to generate minimalist Anthropic-style cover images directly from article content.
Open-source AIGC visual workflows, reusable Agent Skills and real image-generation cases by DerekWen.
Claude Code + Higgsfield ile görsel/video üretim skill'leri — GPT Image 2, Seedance loop'ları, sunum sitesi
Codex skill for image-to-layered-PSD workflows with confirmed single-element extraction
轻量 GPT-Image-2 生图工作台,特别支持批量调用 GPT-Image-2:支持 AI 拆分提示词、队列、重试和图生图 / Lightweight GPT-Image-2 studio with batch calls, AI prompt splitting, queueing, retries, and image-to-image.
Codex/OMX skill for Gemini-to-GPT image style prompt forging
Nano Banana - AI image generation plugin for Claude Code. 13 modes: text-to-image, editing, style transfer, inpainting, 4K, search grounding. Powered by Google Gemini API.
An image upscaling workflow skill based on GPT-6-astra and gpt-image-2.5
Ultimate Gemini 3.1 Flash Image MCP server with 4K generation, Google Search grounding, reference images (up to 14), and thinking mode. Professional image generation made simple.
A Codex skill for planning, generating, evaluating, and refining enterprise architecture diagrams with GPT Image 2.
Local AI image generation for Mac. Run Qwen-Image 2.1 on Apple Silicon, offline and private, with a built-in MCP server for Claude Code and AI agents.
NanoBanana PPT Skills - AI-powered PPT generator with Veo support
Codex skill and TypeScript CLI for 4K AI image generation through self-hosted sub2api OpenAI-compatible endpoints, with streaming, SSE, partial image capture, and Cloudflare 524 timeout mitigation.
MCP server for integrating NovelAI Image generation into AI agents.
MCP server exposing NaN API media tools: image generation/editing (flux-2-klein), TTS (kokoro), STT (whisper), embeddings and rerank
Codex skill for GPT Image 2.5 prompt writing, editing and reference-image workflows. Based on official OpenAI guidance.
Cinematic prompt methodology for AI image and video generation. Install into Claude Code, author director-grade style packs and storyboards from your reference images. Output is markdown, drop-in compatible with PUSHING FRAMES.
DeepSeek Harness plugin: a photo of a surface becomes a complete tileable PBR material set, fully local via ComfyUI (FLUX.2 Klein 4B instruction edit + deterministic PBR derivation). GUI workbench, five agent tools, and a setup tool that finds your ComfyUI and downloads its own weights.
Auto generate and insert image assets during UI coding in Claude Code, using an MCP server for Azure OpenAI gpt-image-1 and Flux-1.1 Pro
多模态 Prompt 逆向工程 Skill:把文本/图片/视频/剧本拆解还原为可复用 Prompt,适配 Midjourney V8.2 / Stable Diffusion 3.5 / FLUX.2 / GPT Image 2.5(文生图·复刻·编辑·参考图·合成五模式)/ Nano Banana Pro / GPT-5.5·Claude 5.5 / DeepSeek V4.1 / Sora 2 / Runway Gen-4.5 / Veo 3.1 十种模型,支持 Claude Code / Cursor / Codex / DeepSeek Harness / 豆包五平台,附百分制六维评分(剧本可逐场景出图)
AI logo maker agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn a brand name, industry, or reference image into logo concepts, brand marks, and app icons with exact brand colors. AI Logo设计 · 品牌标识
MCP server for Krea.ai - Generate stunning AI images & videos with Flux, Hailuo, Runway, Kling, Ideogram, Imagen & more. Works with Claude Desktop, Claude Code, and any MCP client.
Provider-neutral image generation and editing MCP with a Codex Skill. Supports OpenAI Images, Gemini, and chat image APIs.
MCP server enabling high-quality image generation via Together AI's Flux.1 Schnell model.
Fix the issue of being unable to generate images after codex sub2api.
GPT Image 2 ecommerce Skill for product-preserving main images, white-background product photos, PDP prompts, and QA|电商商品图 Agent 工作流
Agent Skill for AI image/video generation via Dreamina (即梦) CLI
AI storyboard generator agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn a script, scene, or ad brief into a practical shot list and a few storyboard key-frame images for film, ads, animation, and social video. AI分镜生成 · 分镜表
An image-generation skill for turning illustrated characters into bold, airy black-ink portraits on clean white. 借助这个图像生成 Skill,可以将单个插画角色转换为纯白底、轮廓有力且留白充足的纯黑墨人物线描。
gpt-image-2 images on your ChatGPT/Codex subscription — no API key, reference images supported. Claude Code skill.
A vendor agnostic MCP server for AI image generation.
A Claude Code skill and toolkit for making AI music videos from a finished song: Midjourney stills, Seedance clips, and every lyric drawn in code on the beat.
[LightX2V](https://x2v.light-ai.top) integration for [OpenClaw](https://openclaw.ai) — image generation (t2i/i2i), video (t2v/i2v/s2v), TTS, and voice clone via cloud API.
Lightweight CLI for AI image generation using Google Gemini API. Text-to-image, image editing, multi-image composition. Perfect for coding agents like Claude Code.
A CLI and agent skill to work with gpt-image-2 using API key or subscription
Design skill for crafting GPT image prompts and generating compact mockups.
Skill for generating covers and infographics for WeChat Official Accounts, Xiaohongshu, Douyin, and other social media platforms. Recommends GPT Image 2.
Claude Code skill that generates optimized Nano Banana 2 (Gemini 3.1) image prompts for ecommerce, marketing, and print-on-demand design
PaperBanana-AIMSLab generates academic figures from methods, captions, or chart intent; supports multi-Agent workflows, API switching, and image-to-image.
买了 gpt-image-2 中转 API 不知道怎么调用?启动即用,填入配置就能生图!A local web UI for image generation APIs — just plug in your API key and start creating.
DeepSeek Harness Image2 生图插件,通过第三方 OpenAI Images 兼容接口调用 gpt-image-2,只需配置 baseURL 和 API Key。 | Image2 generation plugin for DeepSeek Harness via third-party OpenAI Images-compatible APIs.
Image-to-image studio: vision-gated routing + multi-provider generation (DashScope / ChatGPT-web / OpenAI / Z.AI / Doubao / MiniMax) with auto failover. E-commerce sets & photo-art styles. 图生图工作台 · 多供应商自动降级 · 电商套图与照片艺术
Codex skill for academic slides, posters, proofsheets, and architecture diagrams via GPT Image 2
Multi-provider AI image generation cookbook: prompt gallery, agentic skill, and CLI for OpenAI gpt-image-2, Google Imagen, Flux, and more. Claude Code plugin + Codex/OpenClaw skill + Python CLI.
An image-generation skill for Codex that supports base_url + key and stream streaming to reduce long-connection timeouts and disconnects.
Turn any character image into a looping animated sprite (moving SVG, WebP & GIF) with Google's Nano Banana 2 (gemini-3.1-flash-image) — a Claude Code skill.
Codex's image generation in every coding agent: an MCP server + Agent Skill with a one-command installer for opencode, Claude Code, Codex, Cursor, VS Code, Gemini CLI and 20 more tools. Runs on your ChatGPT plan with no API key.
Creative AI MCP server — 32 tools (18 free): image generation, upscaling, bg removal, mockups, CMYK, print-ready PDF, vectorization, watermarking, enrichment, provenance. Pay per call via x402/Stripe/GCX.
A custom skill to generate and then animate an image via Google's Gemini / Nano Banana and Veo models
Run any awesome-gpt-image-2 or Seedance prompt as a one-line Claude Code command. Pay per image with x402 USDC on Base via BlockRun.ai. v1: /headshot, /dance, /poster + 1010-case library.
Generate AI images, videos, speech, and 3D assets from your terminal, Claude Code, or Codex with Atlas Cloud CLI.
Skill bundle for Claude, Codex, Hermes, OpenClaw, Cursor, Windsurf, and generic agents covering PiAPI (Midjourney, Suno, Kling, Flux, Hailuo, Luma, Hunyuan, Faceswap, Trellis 3D, MMAudio, F5-TTS, Veo 3, Gemini 2.5 Flash Image, Seedance, and the OpenAI-compatible LLM gateway).
Turn a one-line idea into a production-grade, copy-paste-ready AI image prompt for posters, landing and UI mockups, ads, game art, and logos. A Claude Code skill optimized for gpt-image-2. MIT.
An extension of Image Gen skill in Codex, it gives you full control to explicitly choose your reference image
This is a frontend design skill specifically tailored for the Codex and GPT-5.6 series models, aiming to enhance the frontend design capabilities of the GPT series models. Through a customized GPT image-compatible API, user interface previews are generated and iterated, and then the approved designs are recreated as high-quality web pages.
Claude Code skill for AI image & video generation with Google Gemini — Nano Banana 2 Lite, Nano Banana Pro, Gemini Omni Flash. Cost gates before paid runs, real reference images, a prompt log beside every file.
Free AI image generation MCP server — no API key, no billing. Nano Banana via Google Flow with your own Google account. Exact pixel sizes, reference images, $0 per image.
镜造 Image Forge — Codex Skill for reference-image distillation, character consistency and AI image generation: preserve hair, expression, pose, body, wardrobe and cinematography.
AI media generator agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: create AI images, video, music, and voice-over, and look up public social data through one connection. AI内容创作 · 图片视频音乐配音生成
Creative Claw: AI video, image and voiceover generation inside ChatGPT, Claude, Codex and Cursor. Seedance 2.5, Gemini Omni, Nano Banana 2, voice cloning. Pay as you go.
Stable local Codex image generation for Hermes/OpenClaw with predictable file output and JSON metadata.
DeepSeek can generate images via an open-source skill and Python script: AI agents understand needs, extract visuals, using Apimart gpt-image-2.
Local control surface to explore FLUX API with additional tools and MCP
Terminal-native AIGC toolkit: multi-provider image/video/audio generation, Midjourney, chat, AIGC forensics, knowledge base, MCP Server. 终端原生 AIGC 工具包:多厂商图片/视频/音频生成、Midjourney、AI 对话、AIGC 取证、知识库、MCP 集成。
Claude Code skill: one reference image → retro scrapbook-style animated short video with Nano Banana keyframes, Kling image-to-video, and copyright checks.
AI image generation skill for coding agents — crafts optimal prompts, generates images via Gemini/Nano Banana, self-reviews, and post-processes. Works with Claude Code, Codex, Gemini CLI, Copilot, and more.
MCP server for Pruna AI — ultra-fast image generation, editing, upscaling, and video generation
AI image/video workflow generator — SKILL.md for Claude, GPTs, Gemini, LangChain, Dify, Coze, and more.
Streaming image generation and editing skill for Codex-compatible OpenAI APIs.
Claude Code image generation skill: generate & edit images with GPT Image 2 (gpt-image-2) from Claude Code via Codex CLI on your ChatGPT subscription. No OpenAI API key. One-line install.
Hermes daily AI image generation skill — photojournalism approach, zero art references
Transform natural language into optimized structured prompts for Gemini image generation. Auto-detects style. Works with OpenClaw and Claude Code.
gpt-image-skills generates or edits images using OpenAI-compatible image APIs configured with base_url and api_key.
Natural, SNS-ready photorealistic portrait prompt skill for Midjourney, Stable Diffusion, Nano Banana, and GPT Image 2.
Standalone MCP server + CLI for ChatGPT image generation (image only), with reliable single-file output
Use your own OpenAI-compatible GPT Image API directly from Codex through MCP, with generation, editing, local originals, and inline previews.
Type a prompt or drop up to 10 photos: Qwen-Image-2.1 renders it on your 12 GB GPU in ~35 s. Desktop app + CLI, honest benchmark vs gpt-image-2.
AI image generator agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: generate, compose, and edit product images, brand visuals, posters, social graphics, illustrations, and photo variations. AI图片生成 · 文生图 · AI修图
AI image realism agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: make AI portraits, product images, and marketing visuals look more natural by fixing plastic skin, malformed hands and faces, repeated textures, and inconsistent lighting. 去AI味 · AI图片修复
🎨 内容配图工作室 · 19 套插画风格 Agent Skill:先读懂文章→挑认知锚点→选风格→可粘贴生图提示词/双后端渲染(gpt-image-2 + Gemini Nano Banana)。Understands your article, picks 1 of 19 illustration styles, emits ready-to-paste prompts.
TROP turns creative briefs into art-directed AI image prompts. Claude Skill and Custom GPT setup.
Image, SVG and video generation for Claude Code: GPT Image 2.5, Nano Banana, Recraft, MiniMax H3, Kling, Seedance and Veo via fal.ai
Agent skill: fetch pose / depth / costume / face reference images from AI reference galleries (POSE-DB-01/02, COSTUME-DB-01, あぎ face DB, CC0 shisei) for GPT Image, Nano Banana, ComfyUI, H3.
生图 / 视频提示词约束引擎 — 把模糊需求变成可执行的提示词。An Agent Skill for constrained image & video prompt engineering (Nano Banana / Seedance / Veo / Sora / Kling / Midjourney / FLUX).
Give Claude Code image generation with your ChatGPT plan: Claude hands the job to Codex and gets the image back. No API key. Free local FLUX fallback on Apple Silicon. An Agent Skill + CLI.
Open-source AI image Skills and GPT Image prompt recipes for Codex—turn photos into doodle stories, crayon art, enamel keepsakes, rubber stamps, editorial paintings, and impasto worlds.
Claude-Codex Connector: let Claude Code use Codex (ChatGPT subscription) to generate images, review code and give second opinions. Skills + installer + docs.
Codex skill for converting complex generated images into clearer, second-editable SVG layouts through model-aware image generation, overview design, element decomposition, and SVG assembly.
Agent skill that generates images through your locally installed, OAuth-authenticated Codex CLI — no API keys, exact-size enforcement, and full prompt archiving for reproducibility.
| Tool | Stars | Score |
|---|---|---|
| ian-xiaohei-illustrations | ★ 13.2k | 77 |
| ip-as-logo-skill | ★ 6.4k | 77 |
| mono-color-skill | ★ 3.6k | 65 |
| skills | ★ 3.8k | 72 |
| paperbanana | ★ 2.5k | 70 |
| MeiGen-AI-Design-MCP | ★ 1.8k | 78 |
| female-portrait-director | ★ 1.7k | 79 |
| ecom-details-image | ★ 1.7k | 70 |
| guizang-material-illustration | ★ 1.3k | 58 |
| banana-claude | ★ 1.2k | 72 |
| codex-ppt-skill | ★ 7.8k | 73 |
| GPT-Image2-Skill | ★ 6.0k | 72 |
| NanoBanana-PPT-Skills | ★ 3.4k | 51 |
| hand-drawn-styles | ★ 2.7k | 72 |
| MiniMax-MCP | ★ 1.6k | 78 |
| ian-handdrawn-ppt | ★ 1.5k | 63 |
| gpt-image2-ppt-skills | ★ 1.4k | 61 |
| ai-image-prompts-skill | ★ 1.4k | 67 |
| comfyui-mcp | ★ 938 | 72 |
| ima2-gen | ★ 904 | 67 |
Claude itself does not output images, but Claude Code can, by calling an image model's API (GPT Image, Nano Banana, FLUX and others) through a skill, an MCP server or directly with your key. In our November 2026 test, Claude Code with no skill and a GPT Image key made a bakery poster with six exact lines of English and Chinese text, a product photo and four matching mascot pictures in 5.1 minutes, for $0.07.
Everything on this page is in the open-source list zhuyansen/awesome-ai-image-skills on GitHub, grouped by model and use. Our test of 130 of them, with every picture each one made, is in the test section above; 20 of those work only with their own service or account, such as Bria, NovelAI, Scenario or Black Forest Labs.
The top image generation tools in 2026 are ian-xiaohei-illustrations, ip-as-logo-skill, mono-color-skill. Agent Skills Hub ranks 265 options by GitHub stars, quality score (9 dimensions, including completeness, examples and agent readiness), and recent activity. The list is rebuilt every 8 hours from live GitHub data.
ian-xiaohei-illustrations (13.2k stars) is the most adopted choice for general image generation workflows. ip-as-logo-skill (6.4k stars) is a strong alternative. Pick by your existing stack: match the language and runtime your team already uses to minimize integration cost. If unsure, start with ian-xiaohei-illustrations — it has the deepest community and the most examples online.
Avoid pre-built image generation tools when (1) your use case requires deep customization that the tool's plugin system doesn't support, (2) you have strict compliance requirements that ban third-party dependencies, (3) the tool's maintenance is inactive (last commit >6 months ago), or (4) your data volume is small enough that a 50-line custom script is cheaper than learning the tool. For most production workflows above 100 requests/day, the time savings from a maintained tool outweigh the customization loss.
Image Generation focuses specifically on image generation skills and mcp servers for claude code, codex and other agents, security-graded: gpt image, nano banana, flux, image editing and design assets. vet before you install. AI Design Tools is a related but distinct category — see https://agentskillshub.top/best/ai-design/ for those tools. The two often appear in the same agent pipeline but solve different problems: choose image generation when your primary goal is the specific task, and ai design tools when the workflow is broader.
For most teams, yes. ian-xiaohei-illustrations has 13.2k stars worth of community testing, handles edge cases you haven't thought of, and ships with documentation. Build your own only when (1) your requirements are deeply non-standard, (2) you have a security/compliance reason to avoid OSS dependencies, or (3) the maintenance burden is small enough (<200 lines of code) that you'll save time long-term. The break-even point is usually around 2-3 weeks of dev time saved.
Most image generation tools listed are open source under permissive licenses (MIT, Apache 2.0). A handful offer paid managed/cloud versions on top of free self-hosted core. Always check the LICENSE file on each tool's GitHub repository before commercial use — some use AGPL or non-commercial restrictions that may not fit your deployment model.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: