Hacker News new | ask | show | jobs
by alextheparrot 912 days ago
LLM + Text-to-Image model is exactly how DALL·E 3 is deployed, fwiw
1 comments
zaptrem 911 days ago
Including the text positioning generation part? What’s the source on that?
link
alextheparrot 911 days ago
The comment was directed at “doesn't this method add another cost and overhead for calling Text-to-Image models”
link
wahnfrieden 911 days ago
No
link