ComfyUI Node: AS_GeminiCaptioning
Category
AS_GeminiCaptioning
Inputs
IMAGE IMAGE
PROMPT TYPE
- SD1.5 – SDXL
- FLUX
APY KEY PATH STRING
GEMINI MODEL
- Gemini 2.0 Flash
- Gemini 2.0 Flash-Lite Preview
- Gemini 1.5 Flash
- Gemini 1.5 Flash-8B
- Gemini 1.5 Pro
PROMPT LENGTH INT
PROMPT REFERENCE STRING
PROMPT STRUCTURE STRING
IGNORE STRING
EMPHASIS STRING
SAVE TO PATH STRING
TXT NAME STRING
Outputs
STRING
STRING
STRING
Extension: AS_GeminiCaptioning Node
A ComfyUI node that combines an image with simple text parameters to create a prompt, sends it to the Google Gemini API via the google-generativeai SDK, and returns the generated text response along with the original prompt and an execution log
Authored by svetozarov
Run ComfyUI workflows in the Cloud!
No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues
Learn more