llm-openai-images 0.3.0

LLM plugin for OpenAI and Google image generation and editing

llm-openai-images

An LLM plugin providing access to OpenAI's gpt-image-1.5 and Google's Nano Banana models for image generation and editing.

Installation

Install this plugin in the same environment as LLM.

llm install llm-openai-images

API Key Setup

You will need API keys for the providers you want to use.

OpenAI:

llm keys set openai

Enter your key when prompted. You can obtain a key from the OpenAI Platform.

Google (Gemini API):

llm keys set gemini

Enter your key when prompted. You can obtain a key from Google AI Studio.

Output Files

The plugin writes images to files and prints the output path. By default, files are written to the current working directory using this naming scheme:

<model>_<timestamp>.png

To override the output path, use -o output:

llm -m openai/gpt-image-1.5 "Prompt..." -o output path/to/file.png

Usage

This plugin adds the following models to LLM:

• openai/gpt-image-1.5
• google/nano-banana
• google/nano-banana-pro

Basic Image Generation

To generate an image from a text prompt:

llm -m openai/gpt-image-1.5 "A cat wearing sunglasses, riding a skateboard"

Generation Options

You can control the image size and quality using options (-o):

• -o size <value>: Set the image dimensions.
  • square (default): 1024x1024
  • portrait: 1024x1536
  • landscape: 1536x1024
• -o quality <value>: Set the image quality/detail.
  • high: ~$0.26
  • medium (default): ~$0.06
  • low: ~$0.015

These options apply to openai/gpt-image-1.5 only. Google Nano Banana models currently ignore them.

Example with options:

llm -m openai/gpt-image-1.5 "Impressionist painting of a harbor at sunset" \
  -o size landscape -o quality high \
  -o output harbor_sunset_hd_landscape.png

Editing an Image

To edit an existing image, provide the image file as an attachment using the -a or --attach flag. The prompt should describe the desired changes or additions to the image.

# First, generate an image or use an existing one (e.g., cat_skateboard.png from above)

# Now, edit it:
llm -m openai/gpt-image-1.5 "Add a small blue bird perched on the cat's head" \
  -a cat_skateboard.png \
  -o output cat_skateboard_with_bird.png

Combining Multiple Images

llm -m openai/gpt-image-1.5 "A photo of me dressed in these pants and top" \
  -a maison-martin-margiela-ss16-blouse.jpg \
  -a dior-homme-19cm-mij.jpg \
  -a me.jpg \
  -o output my_fabulous_self.png

Nano Banana (Google) Examples

llm -m google/nano-banana "A kitten with prominent purple-and-green fur."

llm -m google/nano-banana-pro "A cinematic portrait of a hummingbird" \
  -o output hummingbird.png

Development

To set up this plugin locally, first checkout the code. Then install it in editable mode:

cd llm-openai-images
llm install -e .

See the LLM plugin documentation for more details on plugin development.