Image Generation

Organization

openbotx

image-generation

Generate images from text descriptions using AI. Use when the user asks to create, generate, draw, or design an image, illustration, icon, or any visual content.

Overview

Publisher	openbotx
Repository	`openbotx`
Skill name	`image-generation`
Stars	95
Forks	25
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by openbotx on GitHub. Read the source before you install it.

Installation

Install the Image Generation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/openbotx/openbotx/tree/main/openbotx/skills/image-generation
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/openbotx/openbotx.git /tmp/openbotx
mkdir -p .claude/skills
cp -r /tmp/openbotx/openbotx/skills/image-generation .claude/skills/image-generation

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Image Generation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Image Generation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Image Generation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Image Generation

Generate images using the generate_image tool.

Parameters

Parameter	Type	Required	Description
`prompt`	string	yes	Detailed description of the image
`filename`	string	yes	Output filename (e.g. `poster.png`)
`aspect_ratio`	string	no	`1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `4:5`, `5:4`, `21:9`
`size`	string	no	`1K` (default), `2K`, `4K`
`reference_images`	array	no	Storage paths to reference images
`style`	string	no	Style hint (e.g. `photorealistic`, `illustration`)
`negative_prompt`	string	no	What to avoid (e.g. `blurry, watermark`)
`google_search`	boolean	no	Enable real-time data grounding

Prompt Structure

Build prompts with these 5 components:

Style/medium — photograph, illustration, watercolor, digital art, vector, 3D render
Subject — who or what, with specific details (pose, clothing, expression, material)
Setting — location, time of day, atmosphere, weather
Action — what is happening in the scene
Composition — camera angle, framing (close-up, wide shot, bird's eye, low angle)

Example: "Cinematic photograph of a futuristic city skyline at golden hour, with flying vehicles crossing between skyscrapers, shot from a rooftop balcony with shallow depth of field, warm amber tones"

Aspect Ratio Guide

Choose based on the intended use:

1:1 — social media posts (Instagram feed, profile pictures)
16:9 — banners, landscape, YouTube thumbnails, presentations
9:16 — stories, reels, vertical mobile content
4:3 — classic photo, presentations
3:2 — standard photography
4:5 — Instagram portrait posts
21:9 — ultrawide cinematic banners

Reference Images

Reference images provide visual context. The model sees them BEFORE the text prompt.

For logos and brand assets:

Add the logo path to reference_images
In the prompt, be explicit: "Place the provided logo at the bottom center of the image. Do not modify the logo's shape, colors, or proportions — use it exactly as provided, only resize it to fit the composition"
Never describe what the logo looks like — just describe where and how to use it

For style references:

Add the style image to reference_images
In the prompt: "Generate in the same visual style as the provided reference image"

For editing existing images:

Add the image to reference_images
Describe the desired changes: "Change the background to a sunset beach scene while keeping the subject unchanged"

Text in Images

Enclose exact text in quotes: Write the text "SALE 50% OFF"
Describe typography explicitly: "bold white sans-serif font with a subtle drop shadow"
Specify placement: "centered at the top of the image"
Keep text minimal for social media — one headline maximum to avoid clutter

Google Search Grounding

Set google_search: true when the image needs real-time or factual data:

Stock prices and financial charts
Weather forecasts
Current events and news topics
Sports scores and standings
Real product data

Example: "Visualize the Bitcoin price trend over the last 7 days as an infographic"

Quality Tips

Be descriptive, not repetitive. Don't use "4K, masterpiece, trending on artstation" — the model understands natural language. Describe the scene vividly instead.
Use photographic language for realistic images: camera model, focal length (85mm f/1.4), lighting setup (soft key light with rim light), film stock (Kodak Portra 400)
Be specific about colors and materials: "matte black aluminum with brushed gold accents" instead of just "dark with gold"
Resolution matters: Use size: "2K" for social media, size: "4K" for print-quality assets
Composition keywords: rule of thirds, symmetrical, leading lines, negative space, flat lay, isometric

What NOT to Do

Don't describe reference images — just describe how to USE them
Don't add quality spam keywords — focus on scene description
Don't leave aspect ratio unset for social media — always pick the right ratio
Don't put too much text in the prompt for text-in-image — keep it to one headline
Don't forget to use google_search when the image needs current real-world data

After Generation

Always share the saved file URL with the user so they can preview the result.

Frequently asked questions

What does the Image Generation AI skill do?

Generate images from text descriptions using AI. Use when the user asks to create, generate, draw, or design an image, illustration, icon, or any visual content.

Why use Image Generation on TypingMind?

Because you install it once and use it with any model. Image Generation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Image Generation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openbotx/openbotx/tree/main/openbotx/skills/image-generation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Image Generation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Image Generation?

As many as you like. As long as a model supports skills, you can use Image Generation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Image Generation AI skill free?

Yes. It is published on GitHub by openbotx under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Sketch

NousResearch

OrganizationPopular

Throwaway HTML mockups: 2-3 design variants to compare.

Tldraw Offline

Drive and script tldraw offline canvases with an agent.

Brand Guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual…

Solid

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Image Generation

Parameters

Prompt Structure

Aspect Ratio Guide

Reference Images

Text in Images

Google Search Grounding

Quality Tips

What NOT to Do

After Generation

Frequently asked questions

Related AI Skills

Set up your own AI workspace now