Large Language Models generate human-like text. They operate on words broken up as tokens and predict the next one in a sequence. Image Diffusion models take a static image of noise and iteratively denoise it into a stable image.
The confusion comes from services like OpenAI that take your prompt, dress it up all fancy, and then feed it to a diffusion model.
I’m not sure language models are capable of generating images
No. LLMs are still what generates images.
Large Language Models generate human-like text. They operate on words broken up as tokens and predict the next one in a sequence. Image Diffusion models take a static image of noise and iteratively denoise it into a stable image.
The confusion comes from services like OpenAI that take your prompt, dress it up all fancy, and then feed it to a diffusion model.