# Image to text model that can take an additional text input

**URL:** <https://discuss.huggingface.co/t/image-to-text-model-that-can-take-an-additional-text-input/53920>\
**Category:** 🤗Transformers\
**Created:** [September 7, 2023, 9:05am UTC](https://discuss.huggingface.co/t/image-to-text-model-that-can-take-an-additional-text-input/53920 "2023-09-07T09:05:24Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![nadnadoni1234](https://avatars.discourse-cdn.com/v4/letter/n/85e7bf/32.png) [@nadnadoni1234](https://discuss.huggingface.co/u/nadnadoni1234)\
**Post date:** [September 7, 2023, 9:05am UTC](https://discuss.huggingface.co/t/image-to-text-model-that-can-take-an-additional-text-input/53920/1 "2023-09-07T09:05:24Z")

</div>

Hi, does anyone can recommend an image to text model that can take an additional text input for adding context prior for generating the caption?

---

<div class="post-metadata">

**Author:** ![Sandy1857](https://avatars.discourse-cdn.com/v4/letter/s/ecae2f/32.png) [@Sandy1857](https://discuss.huggingface.co/u/Sandy1857)\
**Post date:** [October 2, 2023, 4:21pm UTC](https://discuss.huggingface.co/t/image-to-text-model-that-can-take-an-additional-text-input/53920/2 "2023-10-02T16:21:31Z")

</div>

I think you can look at Matcha or Deplot models. You could pass in a text along with the image, but I doubt it will have any significant effect on the output, though they were trained with a text-input as well.