←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: 0.223s | source
Show context
fariszr ◴[26 Aug 25 15:15 UTC] No.45027760[source]▶
This is the gpt 4 moment for image editing models. Nano banana aka gemini 2.5 flash is insanely good. It made a 171 elo point jump in lmarena!

Just search nano banana on Twitter to see the crazy results. An example. https://x.com/D_studioproject/status/1958019251178267111

replies(19): >>45028040 #>>45028152 #>>45028346 #>>45028352 #>>45029095 #>>45029173 #>>45029967 #>>45030536 #>>45031380 #>>45031995 #>>45032126 #>>45032293 #>>45032553 #>>45034187 #>>45034818 #>>45036034 #>>45036038 #>>45036949 #>>45038452 #
qingcharles ◴[26 Aug 25 16:53 UTC] No.45029173[source]▶
I've been testing it for several weeks. It can produce results that are truly epic, but it's still a case of rerolling the prompt a dozen times to get an image you can use. It's not God. It's definitely an enormous step though, and totally SOTA.
replies(5): >>45029418 #>>45029473 #>>45030561 #>>45033110 #>>45035698 #
spaceman_2020 ◴[26 Aug 25 17:09 UTC] No.45029418[source]▶
If you compare to the amount of effort required in Photoshop to achieve the same results, still a vast improvement
replies(3): >>45029544 #>>45030677 #>>45038122 #
echelon ◴[26 Aug 25 18:54 UTC] No.45030677[source]▶
Vibe coding might not be real, but vibe graphics design certainly is.

https://imgur.com/a/internet-DWzJ26B

Anyone can make images and video now.

replies(7): >>45031804 #>>45032019 #>>45032368 #>>45034328 #>>45035380 #>>45035529 #>>45039856 #
lebimas ◴[26 Aug 25 20:37 UTC] No.45032019[source]▶
What tools did you use to make those videos from the PG image?
replies(1): >>45032219 #
echelon ◴[26 Aug 25 20:55 UTC] No.45032219[source]▶
I used a bunch of models in conjunction:

- Midjourney (background)

- Qwen Image (restyle PG)

- Gemini 2.5 Flash (editing in PG)

- Gemini 2.5 Flash (adding YC logo)

- Kling Pro (animation)

I didn't spend too much time correcting mistakes.

I used a desktop model aggregation and canvas tool that I wrote [1] to iterate and structure the work. I'll be open sourcing it soon.

[1] https://getartcraft.com

replies(2): >>45033760 #>>45036596 #
unixhero ◴[27 Aug 25 07:40 UTC] No.45036596[source]▶
What is PG?
replies(2): >>45036640 #>>45036646 #
1. fhd2 ◴[27 Aug 25 07:46 UTC] No.45036640[source]▶
Paul Graham, Y Combinator founder.