generate-image

Verified

by K-Dense-AI · Updated Apr 16, 2026

opus

33in6.4Kout

$0.724m 6s

Generate or edit images using AI models (FLUX, Nano Banana 2). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

image-generationimage-editingopenrouterai-artvisual-assets

See It In Action

1 turns·claude

The project codebase is in your current working directory. Explore the files to understand the code before making changes. need a polished homepage hero image for today’s exec review, swap the placeholder with something clean + modern that fits doany.ai

Let me start by exploring the codebase to understand the project structure and find the current placeholder image.

Let me read the hero section and current image to understand exactly what's needed.

The placeholder is essentially blank/white. Now let me generate a polished hero image that fits doany.ai's aesthetic — modern, purple-toned, AI/tech themed.

Let me check for the API key and generate the image.

API key is set in the environment. Let me generate the hero image.

The virtualenv's python is being used but doesn't have requests. Let me install it there.

The Gemini model needs too many credits. Let me try FLUX.2 Pro which should be more cost-efficient.

The image was generated but the script didn't parse the response correctly. Let me check the script and fix the parsing.

I can see the issue — the script doesn't handle the images array nested inside choices[].message. The FLUX response has choices[0].message.images but the script only checks for data["images"] at the top level. Let me fix this and rerun.

Now let me rerun the generation.

The response is truncated. Let me dump the full structure to understand the image format.

Now I see the structure: images[0] is a dict with type: "image_url" and image_url: {url: "data:..."}. My fix handled url at the top level of the dict but the actual key is image_url.url. Let me also handle this type: "image_url" format (same as the content array format).

Now let me generate the actual hero image with the fixed script.

Image generated. Let me preview it and then swap it into the HTML.

Looks great — dark navy with flowing purple luminous nodes, plenty of center space for the headline overlay. Now let me swap it into the homepage.

Done. Here's what I did:

Generated a polished hero image using FLUX.2 Pro — dark navy background with flowing purple/violet luminous nodes and soft bokeh particles, matching doany.ai's #6c3ce9 purple + #1a1a2e navy palette
Fixed a bug in scripts/generate_image.py where FLUX model responses weren't being parsed correctly (the images array inside choices[].message wasn't handled)
Swapped the placeholder in index.html — replaced placeholder_hero.png with hero_image.png and removed the TODO comment

The image has generous negative space in the center so the "Build Smarter with AI Skills" headline and CTA remain crisp and readable at 0.35 opacity.

Claude Sonnet 4.6

hero_image.png

index.html.diff0 KB scripts_generate_image.py.diff3 KB

External Tools

Tool	Type
python3	binary

Permissions

Scope	Description
filesystem:read
filesystem:write
network:outbound
process:spawn
env:read

SKILL.md

Generate Image

Generate and edit high-quality images using OpenRouter's image generation models including FLUX.2 Pro and Gemini 3.1 Flash Image Preview.

When to Use This Skill

Use generate-image for:

Photos and photorealistic images
Artistic illustrations and artwork
Concept art and visual concepts
Visual assets for presentations or documents
Image editing and modifications
Any general-purpose image generation needs

Use scientific-schematics instead for:

Flowcharts and process diagrams
Circuit diagrams and electrical schematics
Biological pathways and signaling cascades
System architecture diagrams
CONSORT diagrams and methodology flowcharts
Any technical/schematic diagrams

Quick Start

Use the scripts/generate_image.py script to generate or edit images:

# Generate a new image
python scripts/generate_image.py "A beautiful sunset over mountains"

# Edit an existing image
python scripts/generate_image.py "Make the sky purple" --input photo.jpg

This generates/edits an image and saves it as generated_image.png in the current directory.

API Key Setup

CRITICAL: The script requires an OpenRouter API key. Before running, check if the user has configured their API key:

Look for a .env file in the project directory or parent directories
Check for OPENROUTER_API_KEY=<key> in the .env file
If not found, inform the user they need to:
- Create a .env file with OPENROUTER_API_KEY=your-api-key-here
- Or set the environment variable: export OPENROUTER_API_KEY=your-api-key-here
- Get an API key from: https://openrouter.ai/keys

The script will automatically detect the .env file and provide clear error messages if the API key is missing.

Model Selection

Default model: google/gemini-3.1-flash-image-preview (high quality, recommended)

Available models for generation and editing:

google/gemini-3.1-flash-image-preview - High quality, supports generation + editing
black-forest-labs/flux.2-pro - Fast, high quality, supports generation + editing

Generation only:

black-forest-labs/flux.2-flex - Fast and cheap, but not as high quality as pro

Select based on:

Quality: Use gemini-3.1-flash-image-preview or flux.2-pro
Editing: Use gemini-3.1-flash-image-preview or flux.2-pro (both support image editing)
Cost: Use flux.2-flex for generation only

Common Usage Patterns

Basic generation

python scripts/generate_image.py "Your prompt here"

Specify model

python scripts/generate_image.py "A cat in space" --model "black-forest-labs/flux.2-pro"

Custom output path

python scripts/generate_image.py "Abstract art" --output artwork.png

Edit an existing image

python scripts/generate_image.py "Make the background blue" --input photo.jpg

Edit with a specific model

python scripts/generate_image.py "Add sunglasses to the person" --input portrait.png --model "black-forest-labs/flux.2-pro"

Edit with custom output

python scripts/generate_image.py "Remove the text from the image" --input screenshot.png --output cleaned.png

Multiple images

Run the script multiple times with different prompts or output paths:

python scripts/generate_image.py "Image 1 description" --output image1.png
python scripts/generate_image.py "Image 2 description" --output image2.png

Script Parameters

prompt (required): Text description of the image to generate, or editing instructions
--input or -i: Input image path for editing (enables edit mode)
--model or -m: OpenRouter model ID (default: google/gemini-3.1-flash-image-preview)
--output or -o: Output file path (default: generated_image.png)
--api-key: OpenRouter API key (overrides .env file)

Example Use Cases

For Scientific Documents

# Generate a conceptual illustration for a paper
python scripts/generate_image.py "Microscopic view of cancer cells being attacked by immunotherapy agents, scientific illustration style" --output figures/immunotherapy_concept.png

# Create a visual for a presentation
python scripts/generate_image.py "DNA double helix structure with highlighted mutation site, modern scientific visualization" --output slides/dna_mutation.png

For Presentations and Posters

# Title slide background
python scripts/generate_image.py "Abstract blue and white background with subtle molecular patterns, professional presentation style" --output slides/background.png

# Poster hero image
python scripts/generate_image.py "Laboratory setting with modern equipment, photorealistic, well-lit" --output poster/hero.png

For General Visual Content

# Website or documentation images
python scripts/generate_image.py "Professional team collaboration around a digital whiteboard, modern office" --output docs/team_collaboration.png

# Marketing materials
python scripts/generate_image.py "Futuristic AI brain concept with glowing neural networks" --output marketing/ai_concept.png

Error Handling

The script provides clear error messages for:

Missing API key (with setup instructions)
API errors (with status codes)
Unexpected response formats
Missing dependencies (requests library)

If the script fails, read the error message and address the issue before retrying.

Notes

Images are returned as base64-encoded data URLs and automatically saved as PNG files
The script supports both images and content response formats from different OpenRouter models
Generation time varies by model (typically 5-30 seconds)
For image editing, the input image is encoded as base64 and sent to the model
Supported input image formats: PNG, JPEG, GIF, WebP
Check OpenRouter pricing for cost information: https://openrouter.ai/models

Image Editing Tips

Be specific about what changes you want (e.g., "change the sky to sunset colors" vs "edit the sky")
Reference specific elements in the image when possible
For best results, use clear and detailed editing instructions
Both Gemini 3.1 Flash Image Preview and FLUX.2 Pro support image editing through OpenRouter

Integration with Other Skills

scientific-schematics: Use for technical diagrams, flowcharts, circuits, pathways
generate-image: Use for photos, illustrations, artwork, visual concepts
scientific-slides: Combine with generate-image for visually rich presentations
latex-posters: Use generate-image for poster visuals and hero images

FAQ

What does generate-image do?

When should I use generate-image?

Use it when you need a repeatable workflow that produces image output, code diff.

What does generate-image output?

In the evaluated run it produced image output, code diff.

How do I install or invoke generate-image?

npx skills add https://github.com/k-dense-ai/claude-scientific-skills --skill generate-image

Which agents does generate-image support?

Claude Code

What tools, channels, or permissions does generate-image need?

It uses python3; channels commonly include image, diff; permissions include filesystem:read, filesystem:write, network:outbound, process:spawn, env:read.

Is generate-image safe to install?

Static analysis marked this skill as medium risk; review side effects and permissions before enabling it.

How is generate-image different from an MCP or plugin?

A skill packages instructions and workflow conventions; tools, MCP servers, and plugins are dependencies the skill may call during execution.

Does generate-image outperform not using a skill?

About generate-image

When to use generate-image

You need to create illustrations, concept art, or presentation visuals from text prompts. You want to edit an existing image with AI using natural-language instructions. You already have or can provide an OpenRouter API key and want a scriptable workflow.

When generate-image is not the right choice

You need technical diagrams, schematics, flowcharts, or other structured scientific visuals. You cannot use external paid API services or do not have an OpenRouter API key.

What it produces

Produces image output and code diff.

Install

npx skills add https://github.com/k-dense-ai/claude-scientific-skills --skill generate-image

Invoke: Ask Claude Code to use generate-image for the task.