I would assume they just have some prompt they are handing to GPT4 (or some other model), with instructions to build it into a deck outline. But how is that deck outline produced by the LLM then getting translated into visuals in powerpoint?
I would assume they just have some prompt they are handing to GPT4 (or some other model), with instructions to build it into a deck outline. But how is that deck outline produced by the LLM then getting translated into visuals in powerpoint?
It seems like it would be split into two layers; the LLM would first plan the presentation based on the user provided prompt and bind it to some kind of template (IE: Title Slide, Big Number, etc) outputting a JSON. Then, take each template and run another LLM call and outputting the details of each slide as another JSON while concurrently running calls to an image creator or image search to fill in the template.