# I want to be able to upload an image and have a story idea generated, based on my criteria

**URL:** <https://discuss.huggingface.co/t/i-want-to-be-able-to-upload-an-image-and-have-a-story-idea-generated-based-on-my-criteria/106391>\
**Category:** Beginners\
**Created:** [September 11, 2024, 11:41pm UTC](https://discuss.huggingface.co/t/i-want-to-be-able-to-upload-an-image-and-have-a-story-idea-generated-based-on-my-criteria/106391 "2024-09-11T23:41:18Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![bradHip](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/bradhip/32/31513_2.png) [@bradHip](https://discuss.huggingface.co/u/bradHip)\
**Post date:** [September 11, 2024, 11:41pm UTC](https://discuss.huggingface.co/t/i-want-to-be-able-to-upload-an-image-and-have-a-story-idea-generated-based-on-my-criteria/106391/1 "2024-09-11T23:41:18Z")

</div>

For a brief time, I paid for chatgpt to see what was possible. One feature I enjoyed was being able to upload a photo (my own or from friends) and then give a set of criteria and have the Ai help me develop a story idea based on the photo. Can I replicate that offline? Or with HuggingFace?

Thank you in advance for any assistance. 🙂

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [September 12, 2024, 4:21am UTC](https://discuss.huggingface.co/t/i-want-to-be-able-to-upload-an-image-and-have-a-story-idea-generated-based-on-my-criteria/106391/2 "2024-09-12T04:21:05Z")

</div>

I saw something similar somewhere on HF. I think I might have one in my collection. I think this one is something close.

> **[Joy Caption Pre Alpha - a Hugging Face Space by fancyfeast](https://huggingface.co/spaces/fancyfeast/joy-caption-pre-alpha)**
>
> Upload an image to get a descriptive caption. The app analyzes the image and provides a detailed description.

Except for the login requirements (which can be confusing and lead to other sites), there is no charge for using Spaces. It is the developer and publisher who pays.

## Some of my collections

> **[Spaces for Image-to-Image / Video - a John6666 Collection](https://huggingface.co/collections/John6666/spaces-for-image-to-image-video)**
>
> Unlock the magic of AI with handpicked models, awesome datasets, papers, and mind-blowing Spaces from John6666

[https://huggingface.co/collections/John6666/spaces-for-llm-vlm-nlp-66999a0f61278f96d85256f4](https://huggingface.co/collections/John6666/spaces-for-llm-vlm-nlp-66999a0f61278f96d85256f4)

> **[Spaces for Tagger / Captioner / Prompter - a John6666 Collection](https://huggingface.co/collections/John6666/spaces-for-tagger-captioner-prompter)**
>
> Unlock the magic of AI with handpicked models, awesome datasets, papers, and mind-blowing Spaces from John6666

## Whole HF Spaces

> **[Spaces - Hugging Face](https://huggingface.co/spaces)**
>
> Discover amazing ML apps made by the community

---

<div class="post-metadata">

**Author:** ![mikehemberger](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/mikehemberger/32/28013_2.png) [@mikehemberger](https://discuss.huggingface.co/u/mikehemberger)\
**Post date:** [September 12, 2024, 9:53am UTC](https://discuss.huggingface.co/t/i-want-to-be-able-to-upload-an-image-and-have-a-story-idea-generated-based-on-my-criteria/106391/3 "2024-09-12T09:53:04Z")

</div>

Hi @bradHip ,  
You can continue to enjoy this feature using ChatGPT. While free-tier limits you somewhat in the number of images you can upload, I can imagine that your work is mostly text/chat-based after you uploaded an image?! If that’s so, ChatGPT is probably still the best option even without a paid subscription.  
In terms of alternatives, you can use almost any vision-(large-)language-model (vLLM) on huggingface. Most have a code usage example on their page. Huggingface offers a wide selection of these vLLMs. Some up-to-date examples:

- [Qwen2-VL](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct)
- [Phi-3.5-Vision](https://huggingface.co/microsoft/Phi-3.5-vision-instruct)

And many many others. If you prefer no-code I’d recommend ChatGPT free tier or some of the spaces that @John6666 linked.  
Best,  
Mike