Hacker News Reader

It means that ChatGPT will be used to optimize your prompts before they are used in DALL-E 3!

The subheading says:

> When prompted with an idea, ChatGPT will automatically generate tailored, detailed prompts for DALL-E 3

Then there’s a video of someone typing into ChatGPT and it responding with images

Every transformer model uses a small/tiny llm (CLIP, OpenCLIP, BLIP2, FLAMINGO) as their text encoder and I guess they use gpt 3.5 for theirs.

even the first version was described by them as gpt: "DALL·E is a 12-billion parameter version of GPT-3", but i am not sure it's the GPT-3 that we know (as trained on all the stuff), but rather like, same/similar architecture? and in other places they mention CLIP as a part of the model (I'm talking about the first version)? all of this is quite confusing for me, and leaves me wondering, if this is simply "same architecture" or "reuse of embeddings" or "use in training" or "fine-tuning", especially for the exciting new version

DALL·E 3 is built natively on ChatGPT

Plus users will be able to directly create images within the ChatGPT web interface.

Marketing I suppose.