e.g. I used stableboost for this earlier tweet 🙂 – the prompt by itself gives bad, too diverse, not amazing results, but once I generated ~1000 I could visually narrow in on the composition I liked. Not sure how I'd get that by tuning the prompt alone
PROMPT ENGINEERING
-
Visual Iteration Over Text Prompts for AI Image Generation
By
–
Sometimes it's difficult to put the look&feel of what you're after into text. You end up re-rolling results over and over again, looking for the needle in a haystack. stableboost flips it around – you create a large haystack of variations, then narrow in on the needle visually.
-
GPT-3 Requires Chain-of-Thought for Problem Solving, Paper Analysis
By
–
Regardless how a human would do it, GPT-3 needs chain-of-thought to perform on these problems. Only skimmed the paper, but I don't see a specific deficit in ToM vs. known inability to do multi-hop inference without CoT.
-
6.4M AI-Generated Images Map Reveals Human Interests
By
–
Worth exploring: a map of 6.4M million images generated by AI, grouped by what the AI considers to similar images.
— Ethan Mollick (@emollick) 1 novembre 2022
Why you might want to explore it: it shows you what kinds of images humans are interested in; it teaches new prompts; & has surprising art.https://t.co/t1oUai8HJNWorth exploring: a map of 6.4M million images generated by AI, grouped by what the AI considers to similar images. Why you might want to explore it: it shows you what kinds of images humans are interested in; it teaches new prompts; & has surprising art.