Does Llama3 use any other model for generating images? Or is it something that llama3 model can do by itself?
Can Llama3 generate images with ollama?
You must log in or # to comment.
Vanilla Llama3 can not generate images. It’s probably just used to write the prompt for a text to image model.
But there’s also some Llama3 based Image/Text to Image/Text models out there, I think.
LLaMA can’t. Chameleon and similar ones can:
There is a LLaVA model, as well as a version fine tuned with LLaMA3, Mistral, or phi3. Go to Ollama.com and search for “llava” under models.
Facebook just didn’t release the code for llama imagegen.
The model you are looking for now is Flux.
