ComfyUI-Gemini
ComfyUI-Gemini enhances content creation and AI interactions with Gemini models, supporting text, image inputs, and file reading.
English
English
The ComfyUI-Gemini plug-in integrates the Google Gemini model into ComfyUI. Users can use the Gemini model to generate prompt words, chat with them, and support multi-modal input such as images. This plug-in is free to use and provides two ways of using API Key, implicit and explicit, suitable for individual and team use.
Demand groups include:
content creator
Users who need AI-assisted conversations
Multimodal interaction users
Example of usage scenario:
Use the Gemini model to generate creative prompt words to assist content creation
Talk to Gemini and get interesting answers and insights
Upload images to Gemini for analysis and description
Product features:
Generate prompt words
Image dialogue
text conversation
multimodal dialogue
file reading
