5 Comments
User's avatar
Mia Kiraki's avatar

Super good advice, thank you!

Expand full comment
Pierre-Eric Jacoupy's avatar

I am wondering now how that logic applies to image generation. It is clear generic LLM like GPT got much better at it, but it does feel the more you try to edit an image generated, the more weird things happen in the background (literally) ? Any insight?

Expand full comment
Jean-Paul Paoli's avatar

I have read stuff on image drift prompt after prompt and personally I reset context often but I didn’t really dig into the matter / experiment enough to get a clear view. Any personal experience ?

Expand full comment
Pierre-Eric Jacoupy's avatar

My experience is so far to get a picture 80% there at first prompt, able to refine it at 90% on a second or third iteration but at fourth & beyond it starts to behave and significantly become off track. That’s just empirical. It is much better when getting pictures in attachment as style or tone reference.

Expand full comment
Pierre-Eric Jacoupy's avatar

I have learned recently that LLM predicts the next best token similarly between text token, audio bits taken (natural conversation) and image / pixel bits token.

Expand full comment