Generate Image

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:

1. Look for a .env file in the project directory or parent directories
2. Check for OPENROUTER_API_KEY=<key> in the .env file
3. 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 (standard quality, recommended)

Use google/gemini-3.1-flash-image-preview by default for both generation and editing. Treat this as the house default unless the user explicitly asks for a different model.

Alternative models:

• black-forest-labs/flux.2-pro - alternative option for generation + editing when the user explicitly requests it
• black-forest-labs/flux.2-flex - cheaper generation-only fallback when needed

Default to standard quality. Do not optimize for premium/high-fidelity output unless the user explicitly asks for that.

Common Usage Patterns

Basic generation

python scripts/generate_image.py "Your prompt here"

Specify model explicitly only when needed

python scripts/generate_image.py "A cat in space" --model "google/gemini-3.1-flash-image-preview"

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 the default model explicitly

python scripts/generate_image.py "Add sunglasses to the person" --input portrait.png --model "google/gemini-3.1-flash-image-preview"

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; only override when the user explicitly asks)
• --output or -o: Output file path (default: generated_image.png)
• --api-key: OpenRouter API key (overrides .env file)

Image Post-Processing

After generation, the script automatically:

1. Resizes the image to a maximum width of 500px (aspect ratio preserved).
2. Targets blog-cover-friendly file sizes: aims for roughly 200KB and keeps the final file at about 220KB or less when possible.
3. Chooses the delivery format automatically for blog-cover usage:
   • WebP for simpler/cleaner illustrations, graphics, or images with transparency.
   • JPEG for more texture-heavy, photo-like, or high-complexity images.
4. Compresses aggressively when needed: adjusts quality and, if necessary, slightly reduces dimensions further. If the generated PNG is replaced during post-processing, the final output will usually become a .webp or .jpg file.

This keeps cover images lightweight and suitable for blog use without leaving oversized assets behind. The Pillow library is required for post-processing:

pip install Pillow

If Pillow is not installed, a warning is printed and post-processing is skipped.

Cover Image Guidance

When using this skill for blog cover images or social preview artwork:

• Prefer concise, visually strong compositions that still look good after resizing.
• Assume the final asset should land around 200KB on disk.
• Expect the script to return a post-processed .webp or .jpg path rather than preserving the original PNG extension.
• After generation, verify the saved file size and use the post-processed output path returned by the script.
• If an image still ends up larger than expected, rerun with a simpler composition or fewer high-frequency details.

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.

Critical Prompt Requirements

IMPORTANT: No Meta Instructions in Output

When generating prompts for the AI image generation models, ensure the generated image does NOT contain any visible text showing:

• The prompt or instructions that were given to generate it
• System instructions or AI-related metadata
• Any "meta" text describing how the image was created
• Watermarks or labels indicating AI generation
• Layout descriptions (e.g., "left panel", "right panel", "center panel")
• Font specifications or typography instructions
• Color scheme descriptions or palette information

The image should only contain the requested visual content. Always include this instruction in your prompts: "Do not include any text showing the prompt, instructions, layout descriptions, font/color specifications, or metadata in the generated image."

Notes

• Images are returned as base64-encoded data URLs and are then post-processed into blog-friendly output, usually .webp or .jpg
• The script supports both images and content response formats from different OpenRouter models
• Generation time varies by model (typically 5-30 seconds)
• Default to standard-quality output; avoid expensive premium settings unless requested
• 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 Pro 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