Gemini Image 2 Prompt

GeminiImageToPrompt

Extract subject + background + style + language from 2 images via OpenAI vision model.

Pack: AI_Text_Comfyui

custom_nodes.AI_Text_Comfyui

Inputs (4)

Name	Type	Required
api_key	STRING	required
main_image	IMAGE	required
background_image	IMAGE	required
model	COMBO	required

Outputs (1)

Name	Type
prompt	STRING

Gemini Image 2 Prompt | TealPug Node Explorer