This extension integrates Google's Gemini API, Ollama, and various image processing tools into ComfyUI, allowing users to leverage these powerful models and features directly within their ComfyUI workflows.
- Support for Gemini and Ollama APIs
- Text and image input capabilities
- Streaming option for real-time responses
- FLUX Resolution tools for image sizing
- ComfyUI Styler for advanced styling options
- Raster to Vector (SVG) conversion
- Text splitting and processing
- Easy integration with ComfyUI workflows
The Gemini API node allows you to interact with Google's Gemini models:
- Text input field for prompts
- Model selection:
- gemini-1.5-pro-latest
- gemini-1.5-pro-exp-0801
- gemini-1.5-flash
- Streaming option for real-time responses
Integrate local language models running via Ollama:
- Text input field for prompts
- Dropdown for selecting Ollama models
- Customizable model options
Provides advanced image resolution and sizing options:
- Predefined resolution presets (e.g., 768x1024, 1024x768, 1152x768)
- Custom sizing parameters:
- size_selected
- multiply_factor
- manual_width
- manual_height
Extensive styling options for various creative needs:
- Advertising styles (e.g., automotive, corporate, fashion editorial)
- Art styles (e.g., abstract, art deco, cubist, impressionist)
- Futuristic styles (e.g., biomechanical, cyberpunk)
- Additional categories like composition, environment, and texture
Convert raster images to vector graphics and save them:
Raster to Vector node parameters:
- colormode
- filter_speckle
- corner_threshold
- ... (and more)
Save SVG node options:
- filename_prefix
- overwrite_existing
Split text based on specified delimiters:
The RMBG
node allows you to remove the background from images using the BRIA model.
- Model Download: RMBG-1.4 model
- Model Location: Download and place the model file in
ComfyUI/custom_nodes/ComfyUI-OllamaGemini/RMBG-1.4/
.
Inputs:
rmbgmodel
: Path to the RMBG model.image
: The image from which the background will be removed.
Outputs:
image
: The image with the background removed.mask
: The mask representing the removed background.
Usage:
- Load the RMBG model using the
BRIA_RMBG Model Loader
node. - Connect the output
rmbgmodel
to theRMBG
node. - Input the image you want to process, and connect it to the
RMBG
node'simage
input. - The output
image
will be the image with the background removed, and themask
output will provide the corresponding mask.
-
Clone this repository into your ComfyUI's
custom_nodes
directory:cd /path/to/ComfyUI/custom_nodes git clone https://github.com/yourusername/GeminiOllama.git
-
Install the required dependencies:
pip install google-generativeai vtracer
-
Obtain a Gemini API key from the Google AI Studio. https://aistudio.google.com/app/u/1/apikey
-
in
config.json
file in the extension directory:{ "GEMINI_API_KEY": "your_api_key_here" }
-
Install Ollama following the instructions on the Ollama GitHub page.
-
Start the Ollama server (usually runs on http://localhost:11434).
-
(Optional if you change ollama host) Add the Ollama URL to your
config.json
:{ "GEMINI_API_KEY": "your_api_key_here", "OLLAMA_URL": "http://localhost:11434" }
After installation and configuration, the new nodes will be available in ComfyUI. Drag and drop them into your workflow to start using their features.
Contributions are welcome! Please feel free to submit a Pull Request.
This project is licensed under the MIT License - see the LICENSE file for details.