hermes-stepfun-imagegen 0.1.0

StepFun image generation backend for Hermes Agent (step-image-edit-2, step-2x-large, step-1x-medium).

Hermes StepFun ImageGen

StepFun image generation backend for Hermes Agent.

Supports StepFun's image models:

• step-image-edit-2 — recommended, fast text-to-image + image editing (1-2s)
• step-2x-large — high-quality text-to-image / image-to-image
• step-1x-medium — balanced quality and speed

Installation

From PyPI (once published)

pip install hermes-stepfun-imagegen

From source

git clone https://github.com/lora-sys/hermes-stepfun-imagegen.git
cd hermes-stepfun-imagegen
pip install -e .

Manual install

Copy the plugin directory to your Hermes plugins folder:

cp -r src/hermes_stepfun_imagegen ~/.hermes/plugins/image_gen/stepfun

Configuration

1. Set your StepFun API key

Add to ~/.hermes/.env:

STEPFUN_API_KEY=your-stepfun-api-key

Or export it in your shell:

export STEPFUN_API_KEY=your-stepfun-api-key

2. Enable the plugin

Add to ~/.hermes/config.yaml:

plugins:
  enabled:
    - image_gen/stepfun

image_gen:
  provider: stepfun
  model: step-image-edit-2  # optional, defaults to step-image-edit-2

3. Restart Hermes

hermes gateway restart

Or restart the Hermes desktop app.

Usage

Once configured, the Hermes model can call image_generate directly:

Text-to-image:

生成一张赛博朋克风格的龙

Image editing:

把这张图换成水墨画风格

(with an image URL or file)

Image-to-image:

把这张照片转成梵高风格

Model Selection

Change the default model in config.yaml:

image_gen:
  provider: stepfun
  model: step-2x-large  # or step-1x-medium

Available models:

Model	Speed	Best for
step-image-edit-2	~1-2s	Fast iteration, text-to-image + editing
step-2x-large	~10-20s	High quality, image-to-image
step-1x-medium	~10-20s	Balanced quality and speed

API Reference

• StepFun 开放平台: https://platform.stepfun.com
• API 文档: https://platform.stepfun.com/docs/zh/api-reference/images/image

Development

# Install in editable mode
pip install -e .

# Run tests
python -m pytest tests/

# Build package
python -m build

License

MIT

Author

lora-sys