# Model that can generate both text and image as output
**URL:**
**Author:**  [@BibhutiPadhi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FBibhutiPadhi)%5C
**Post date:** [December 19, 2024, 6:29am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-that-can-generate-both-text-and-image-as-output%2F132209%2F1 "2024-12-19T06:29:41Z")
Greetings.
Would it be possible to suggest models that can generate both text and images based on text only prompt.
---
**Author:**  [@Alanturner2](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAlanturner2)%5C
**Post date:** [December 19, 2024, 7:13am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-that-can-generate-both-text-and-image-as-output%2F132209%2F2 "2024-12-19T07:13:37Z")
I think that your idea is part of the any-to-any model.
And you can also generate text or images using two models that combined llm and diffusion model.
But if we combine them that is any-to-any model. I know that there isn’t any model have this ability.
It’s ongoing to develop.
---
**Author:**  [@BibhutiPadhi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FBibhutiPadhi)%5C
**Post date:** [December 19, 2024, 8:20am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-that-can-generate-both-text-and-image-as-output%2F132209%2F3 "2024-12-19T08:20:48Z")
Thanks @Alanturner2 for the feedback.
So the only way I see now is to integrate the two models by passing the generated text to a diffusion model for which images are required.
Then as a final step merge the text and images into a single output.
---
**Author:**  [@Alanturner2](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAlanturner2)%5C
**Post date:** [December 19, 2024, 8:42am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-that-can-generate-both-text-and-image-as-output%2F132209%2F4 "2024-12-19T08:42:43Z")
Yeah that’s right.
You can use LLM and diffusion as a base model .
And than you can add encoder or decoder part for diffusion model.
Than you can generate image and text at the same time.
---
**Author:**  [@godofprogrammer](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fgodofprogrammer)%5C
**Post date:** [December 21, 2024, 11:02am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-that-can-generate-both-text-and-image-as-output%2F132209%2F5 "2024-12-21T11:02:40Z")
> [@Alanturner2](#):
>
> e
it truly looks fascinating mate! I have not used anything like this before. Interesting
---
**Author:**  [@ValdeJunior](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FValdeJunior)%5C
**Post date:** [December 31, 2024, 12:15am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-that-can-generate-both-text-and-image-as-output%2F132209%2F6 "2024-12-31T00:15:42Z")
There are many models that accept your condition.
1.OpenAI GPT 4
this is perhaps the most advanced option for multimodal capabilities.
2.Google DeepMind’s Gemini
3. Midjourney and stable diffusion
4. CLIP and Artbreeder