gemini-image-simpleGenerate and edit images with Gemini API using pure Python stdlib. Zero dependencies - works on locked-down environments where pip/uv aren't available.
Install via ClawdBot CLI:
clawdbot install Cluka-399/gemini-image-simpleGenerate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) - the highest quality image generation model.
| Feature | This Skill | Others (nano-banana-pro, etc.) |
|---------|------------|-------------------------------|
| Dependencies | None (stdlib only) | google-genai, pillow, etc. |
| Requires pip/uv | â No | â Yes |
| Works on Fly.io free | â Yes | â Fails |
| Works in containers | â Yes | â Often fails |
| Image generation | â Full | â Full |
| Image editing | â Yes | â Yes |
| Setup complexity | Just set API key | Install packages first |
Bottom line: This skill works anywhere Python 3 exists. No package managers, no virtual environments, no permission issues.
# Generate
python3 /data/clawd/skills/gemini-image-simple/scripts/generate.py "A cat wearing a tiny hat" cat.png
# Edit existing image
python3 /data/clawd/skills/gemini-image-simple/scripts/generate.py "Make it sunset lighting" edited.png --input original.pngpython3 {baseDir}/scripts/generate.py "your prompt" output.pngpython3 {baseDir}/scripts/generate.py "edit instructions" output.png --input source.pngSupported input formats: PNG, JPG, JPEG, GIF, WEBP
Set GEMINI_API_KEY environment variable. Get one at https://aistudio.google.com/apikey
Uses Nano Banana Pro (nano-banana-pro-preview) - Google's highest quality image generation model:
urllib.request for HTTP (no requests library)json for parsing (stdlib)base64 for encoding (stdlib)That's it. No external packages. Works on any Python 3.10+ installation.
Currently using: nano-banana-pro-preview (also known as Gemini 3 Pro Image)
Other available models (can be changed in generate.py if needed):
gemini-3-pro-image-preview - Same as Nano Banana Proimagen-4.0-ultra-generate-001 - Imagen 4.0 Ultraimagen-4.0-generate-001 - Imagen 4.0gemini-2.5-flash-image - Gemini 2.5 Flash with image gen# Landscape
python3 {baseDir}/scripts/generate.py "Misty mountains at sunrise, photorealistic" mountains.png
# Product shot
python3 {baseDir}/scripts/generate.py "Minimalist product photo of a coffee cup, white background" coffee.png
# Edit: change style
python3 {baseDir}/scripts/generate.py "Convert to watercolor painting style" watercolor.png --input photo.jpg
# Edit: add element
python3 {baseDir}/scripts/generate.py "Add a rainbow in the sky" rainbow.png --input landscape.pngGenerated Mar 1, 2026
Online retailers can generate high-quality product images for listings without photoshoots, saving costs and time. This is ideal for startups or small businesses launching new items, enabling rapid prototyping of visual content.
Marketing teams can produce custom images for social media, ads, or blog posts based on specific prompts, enhancing campaign personalization. It supports quick edits to existing visuals, such as adjusting lighting or adding elements, for agile content updates.
Educators and content creators can generate illustrative images for textbooks, presentations, or online courses to explain complex concepts visually. The skill allows editing existing diagrams or photos to better suit learning objectives without graphic design expertise.
Artists and designers can use this to brainstorm ideas, create digital art, or modify images for projects like book covers or game assets. Its dependency-free nature makes it accessible in constrained environments like shared servers or containers.
Real estate agents can edit property photos to enhance appeal, such as adding furniture or adjusting lighting, without expensive software. This helps in creating attractive listings quickly, especially for remote or budget-conscious operations.
Offer a basic free tier for limited image generations, with paid plans for higher volumes or advanced features like batch processing. This attracts small users and scales with enterprise clients needing custom integrations.
License the skill to other platforms or businesses as an embedded image generation tool, charging per integration or user. This leverages the zero-dependency advantage for easy deployment in third-party applications.
Provide services to tailor the skill for specific industries, such as automating image creation for e-commerce or integrating with existing workflows. Charge for setup, training, and ongoing support.
đŹ Integration Tip
Ensure the GEMINI_API_KEY is securely set as an environment variable, and use the provided scripts directly in automation pipelines for seamless image generation.
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Capture frames or clips from RTSP/ONVIF cameras.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
äœżçšć çœź image_generate.py èæŹçæćŸç, ćć€æž æ°ć ·äœç `prompt`ă
AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style transfer. Professional image creation with AI.