ComfyUI_Gemini_Flash is a custom node for ComfyUI, integrating the capabilities of the Gemini 1.5 Flash model. This node supports text and vision-based prompts, allowing users to analyze and adapt images to text prompts for text2image tasks.
ComfyUI_Gemini_Flash is a custom node for ComfyUI, integrating the capabilities of the Gemini 1.5 Flash model. This node supports text and vision-based prompts, allowing users to analyze and adapt images to text prompts for text2image tasks.
config.json
is in the root directory of the node.vision
option as needed.This node now includes support for using proxies, which is particularly useful in regions where the Gemini Flash model is not freely accessible.
http(s)://PROXY_USER:PROXY_PASS@PROXY_ADDRESS:PROXY_PORT
The Gemini 1.5 Flash model by Google is designed to be the fastest and most cost-efficient model for high volume tasks. It addresses developers' needs for lower latency and cost, making it ideal for large-scale applications. With a rate limit increased to 1000 requests per minute and the removal of the request per day limit, Gemini 1.5 Flash provides robust performance for demanding applications. Additionally, tuning support for the model is available, allowing for customization to meet specific performance thresholds without additional per-token costs.
This project was made possible thanks to the contributions of the ComfyUI community and the developers of the Gemini model at Google. Special thanks to all the contributors and users for their continuous support and feedback.