←back to thread

Gemini 2.5 Flash Image

(developers.googleblog.com)
1092 points meetpateltech | 1 comments | 26 Aug 25 14:01 UTC | HN request time: 0s | source
Show context
kemyd ◴[26 Aug 25 15:55 UTC] No.45028284[source]▶
I don't get the hype. Tested it with the same prompts I used with Midjourney, and the results are worse than in Midjourney a year ago. What am I missing?
replies(4): >>45028310 #>>45028315 #>>45028333 #>>45029208 #
cdrini ◴[26 Aug 25 15:56 UTC] No.45028315[source]▶
Hmm, I think the hype is mainly for image editing, not generating. Although note I haven't used it! How are you testing it?
replies(2): >>45028371 #>>45029411 #
1. qingcharles ◴[26 Aug 25 17:08 UTC] No.45029411[source]▶
It actually has impressive image generating ability, IMO. I think the two things go hand-in-hand. Its prompt adherence can be weaker than other models, though.