ComfyUI-IF_AI_tools is a set of custom nodes for ComfyUI that allows you to generate prompts using a local Large Language Model (LLM) via Ollama. This tool enables you to enhance your image generation workflow by leveraging the power of language models.
From what I can tell, each message must have a text (and an optional image), but theres no way for 1 message to have multiple images in it (https://github.com/if-ai/ComfyUI-IF_AI_tools/blob/989282a2bb4d77f2a10de5af3d3dd959a792f838/openai_api.py#L56)
Is there a way to mimic this API: https://platform.openai.com/docs/guides/vision/multiple-image-inputs