Nodes/Sage Utils/LLM Prompt (Vision)
ComfyUI Node

LLM Prompt (Vision)

Unified provider-switching vision generation node for REST/OpenAI and Native CLIP.

By arcum42·Created 2 years ago·Updated 24 days ago· 32
LLM Prompt (Vision)
  • image
  • response
promptWrite a detailed description for this image. Use precise, unambiguous language. Avoid vague or general terms. This is going to be used as input for an AI image generator, so do not include anything other than the description, and do not break things into sections or use markdown.
provider
seed0
CategorySage Utils/LLM

Inputs (4)

NameTypeDefaultDescription
promptSTRINGWrite a detailed description for this image. Use precise, unambiguous language. Avoid vague or general terms. This is going to be used as input for an AI image generator, so do not include anything other than the description, and do not break things into sections or use markdown.The text prompt for vision-capable LLM providers.
imageIMAGEThe reference image sent to the vision provider.
providerCOMBOPick the backend provider and its model/runtime settings.
seedINT00–4294967295Base seed used by all providers (provider-specific behavior may vary).

Outputs (1)

NameTypeDescription
responseSTRINGThe text response returned by the selected vision provider.