---
title: "AutoModelForImageTextToText"
sidebar_label: "AutoModelForImageTextToText"
description: "The clika_runtime.modelverse.auto AutoModelForImageTextToText class."
---

<!-- Generated by tools/api_reference/generate_api_docs.py. Do not edit. -->

Load a vision-language text-generation model by name (a picture and a
    prompt in, text out): a :class:`GenerativeModel`.