
gemini-imagen
Generate images using Google Gemini APIs with post-processing options
- version
- 1.0.0
Install
/plugin install gemini-imagen@notque-gemini-imagenRun it inside Claude Code after adding the marketplace with /plugin marketplace add notque/gemini-imagen.
Contents
Discovered from sourceSkills 1
Gemini Imagen
Generate images from text prompts using Google's Gemini APIs. This plugin gives Claude Code the ability to generate images directly.
Quick Start
# Generate an image
python3 ~/.claude/plugins/gemini-imagen/skills/gemini-imagen/scripts/generate_image.py \
--prompt "A cute cartoon cat" \
--output cat.png
CRITICAL: Exact Model Names
Use ONLY these exact model strings:
| Model String | Speed | Best For |
|---|---|---|
gemini-2.5-flash-image | Fast (2-5s) | Drafts, iterations |
gemini-3-pro-image-preview | Slower (5-15s) | Quality, text rendering, 2K |
Common mistakes:
gemini-2.5-flash-preview-05-20- WRONG (date suffixes are for text models)gemini-2.5-pro-image- WRONG (doesn't exist)gemini-3-flash-image- WRONG (doesn't exist)
Instructions
Step 1: Check API Key
echo "GEMINI_API_KEY is ${GEMINI_API_KEY:+set}"
If not set, tell the user to run /imagen:setup.
Step 2: Install Dependencies
pip install google-genai Pillow
Step 3: Generate Image
python3 ~/.claude/plugins/gemini-imagen/skills/gemini-imagen/scripts/generate_image.py \
--prompt "YOUR PROMPT HERE" \
--output /path/to/output.png
Step 4: Verify Output
ls -la /path/to/output.png
Model Selection
| Use Case | Model | Why |
|---|---|---|
| Iterating on prompts | gemini-2.5-flash-image | Fast feedback (2-5s) |
| Final asset | gemini-3-pro-image-preview | Best quality |
| Game sprites | gemini-2.5-flash-image | Many images, consistent |
| Text in image | gemini-3-pro-image-preview | Better typography |
| Batch generation | gemini-2.5-flash-image | Cost effective |
Post-Processing Options
Remove Watermarks (--remove-watermark)
Removes bright pixels from image corners. Very useful for cleaning up generated images.
Background Transparency (--transparent-bg)
Converts solid-color backgrounds to transparent. Great for sprites and icons.
python3 generate_image.py \
--prompt "Character on gray background" \
--output char.png \
--remove-watermark \
--transparent-bg
Batch Generation
Generate multiple images from a file:
# prompts.txt (one per line)
python3 generate_image.py \
--batch prompts.txt \
--output-dir ./images/
Error Handling
| Error | Solution |
|---|---|
GEMINI_API_KEY not set | Run /imagen:setup |
Rate limit (429) | Wait 60s, script auto-retries |
Content policy (400) | Modify prompt |
No image in response | Add more detail to prompt |
Pillow not installed | Run pip install Pillow |
Script Reference
Location: scripts/generate_image.py
| Argument | Required | Description |
|---|---|---|
--prompt | Yes* | Text prompt |
--output | Yes* | Output file path (.png) |
--model | No | Model (default: gemini-3-pro-image-preview) |
--remove-watermark | No | Remove corner watermarks |
--transparent-bg | No | Make background transparent |
--bg-color | No | Background hex color (default: #3a3a3a) |
--batch | No | Prompts file (one per line) |
--output-dir | No | Directory for batch output |
*Required unless using --batch
Exit Codes:
- 0: Success
- 1: Missing API key
- 2: Generation failed
- 3: Invalid arguments
What This Plugin CAN Do
- Generate images from text prompts
- Select between fast and quality models
- Remove watermarks from images
- Make backgrounds transparent
- Batch generate multiple images
What This Plugin CANNOT Do
- Use non-Gemini models (DALL-E, Midjourney, Stable Diffusion)
- Generate video or audio
- Bypass content policy restrictions
Commands 2
Gemini Imagen Help
Commands
| Command | Description |
|---|---|
/imagen | Generate an image |
/imagen:setup | Setup API key |
/imagen:help | This help |
Models
| Model | Speed | Use For |
|---|---|---|
gemini-2.5-flash-image | 2-5s | Drafts, iterations |
gemini-3-pro-image-preview | 5-15s | Quality, text |
Quick Generate
python3 ~/.claude/plugins/gemini-imagen/skills/gemini-imagen/scripts/generate_image.py \
--prompt "A cute cartoon cat" \
--output cat.png
Options
| Flag | Description |
|---|---|
--prompt | Text prompt |
--output | Output file (.png) |
--model | Model selection |
--remove-watermark | Clean corner watermarks |
--transparent-bg | Transparent background |
--batch | Prompts file |
Troubleshooting
| Error | Fix |
|---|---|
| API key missing | /imagen:setup |
| Rate limited | Wait 60s |
| No Pillow | pip install Pillow |
Gemini Imagen Setup
Step 1: Get Your API Key
- Go to Google AI Studio
- Sign in with Google
- Click "Create API Key"
- Copy the key
Step 2: Set Environment Variable
macOS / Linux (zsh):
echo 'export GEMINI_API_KEY="your_key_here"' >> ~/.zshrc && source ~/.zshrc
macOS / Linux (bash):
echo 'export GEMINI_API_KEY="your_key_here"' >> ~/.bashrc && source ~/.bashrc
Windows PowerShell:
[Environment]::SetEnvironmentVariable("GEMINI_API_KEY", "your_key_here", "User")
# Restart terminal
Windows CMD:
setx GEMINI_API_KEY "your_key_here"
:: Restart terminal
Step 3: Install Dependencies
pip install google-genai Pillow
Step 4: Verify
echo "GEMINI_API_KEY is ${GEMINI_API_KEY:+set}"
Should output: GEMINI_API_KEY is set
Troubleshooting
Key not found after setting:
- Restart your terminal
- Check the correct shell config file (.zshrc vs .bashrc)
Invalid API key error:
- Verify the key was copied correctly (no extra spaces)
- Ensure the key is for Gemini API (not Vertex AI)
pip install fails:
- Try
pip3 install google-genai Pillow - Or use
python3 -m pip install google-genai Pillow
Sponsors
Details
- Marketplace
- notque/gemini-imagen
- Source
- .
- Author
- notque
- Category
- Development