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-1.5google/nano-bananagoogle/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): 1024x1024portrait: 1024x1536landscape: 1536x1024
-o quality <value>: Set the image quality/detail.high: ~$0.26medium(default): ~$0.06low: ~$0.015
These options apply to openai/gpt-image-1.5 only. Google Nano Banana models currently ignore them.
For Google Nano Banana models, you can set:
-o aspect_ratio <value>: Set the image aspect ratio (default:1:1).1:1,2:3,3:2,3:4,4:3,4:5,5:4,9:16,16:9,21:9
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.
Metadata
Release files for llm-openai-images 0.3.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| llm_openai_images-0.3.1.tar.gz | 10.4 kB | Without provenance | Details for llm_openai_images-0.3.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| llm_openai_images-0.3.1-py3-none-any.whl | Python 3 | none | any | Details for llm_openai_images-0.3.1-py3-none-any.whl |
Total release size: 21.4 kB
Release files / llm_openai_images-0.3.1.tar.gz
| Download URL | llm_openai_images-0.3.1.tar.gz |
|---|---|
| Size | 10.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2e25cbf8cbdcf9bf017e2c6b7e183dc9cf570794e989209353d6d2effb10d60b
|
|
BLAKE2b-256 checksum How to use checksums |
4f10a18ad31464fa6754df831dd1c42c9b284c6a17884f1258cdb029017f9f21
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.2
|
Release files / llm_openai_images-0.3.1-py3-none-any.whl
| Download URL | llm_openai_images-0.3.1-py3-none-any.whl |
|---|---|
| Size | 11.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
60b0a6bbf5e49a7292d5adb545b2bceedd91ed13aa98dfae9d736e251b9bc27b
|
|
BLAKE2b-256 checksum How to use checksums |
85b12a161f44641a2e2f43085fbb68c3aaf6d4c65574e4c09f57203a879531bc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.2
|
Security for llm-openai-images 0.3.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.