Gemini 2.5 Flash Image • Hacker News Board

Re: Gemini 2.5 Flash Image

#491

Post by bacchusracine » Thu, Aug 28, 2025, 12:44 PM UTC

spaceman_2020 wrote: post #345

echelon wrote: post #268

Earlier quoted context omitted.

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.

Midjourney with style references is just about the easiest way right now for an absolute noob to get good aesthetics

This post may or may not violate our community standards so we aren't going to display it.

Re: Gemini 2.5 Flash Image

#492

Post by asadm » Thu, Aug 28, 2025, 7:23 PM UTC

ojr wrote: post #395

asadm wrote: post #226

this is amazing. I just wish models would have more non-textual controls. I don't want to TYPE my instructions. We need a better UI for editing images with AI.

You want to use a mouse and keyboard and learn 20 buttons like it's 1990?

yes! for extremely precise edits.

Re: Gemini 2.5 Flash Image

#493

Post by leegrayson2023 » Thu, Aug 28, 2025, 11:52 PM UTC

[dead]

Re: Gemini 2.5 Flash Image

#494

Post by atonse » Fri, Aug 29, 2025, 4:47 AM UTC

atleastoptimal wrote: post #384

I can imagine an automated blackmail bot that scrapes image, video, voice samples from anyone with the most meagre online presence, which then creates high resolution videos of that person doing the most horrid acts, then threatening to share those videos with that person's family, friends and business contacts unless they are paid $5000 in a cryptocurrency to an anonymous address. And further, I can imagine some per…

I’m also wondering if the opposite will be true. That people might claim something is AI generated to discredit it?

Re: Gemini 2.5 Flash Image

#495

Post by dallen97 » Fri, Aug 29, 2025, 8:42 AM UTC

Been testing both Flux Krea and Nano Banana for image editing tasks. Honestly, they’re closer than people think. Flux Krea nails character consistency and semantic edits—especially when working with multi-turn prompts. Nano Banana (aka Gemini 2.5 Flash) feels snappier and handles multi-image composition surprisingly well.

I used this test site to benchmark them side by side. https://flux-krea.app/ Results? Comparable quality, but different strengths. Flux is better for precision edits and prompt adherence. Nano Banana shines in speed and creative blending. Pick your tool based on workflow, not hype.

Re: Gemini 2.5 Flash Image

#496

Post by lisa0612 » Fri, Aug 29, 2025, 10:33 AM UTC

[dead]

Re: Gemini 2.5 Flash Image

#497

Post by wtarreau » Fri, Aug 29, 2025, 6:14 PM UTC

Just doesn't work for me, it says "here's the combined image" after ~10s but shows nothing at all. Maybe already victim of its success ?

Re: Gemini 2.5 Flash Image

#498

Post by smallflykk » Sat, Aug 30, 2025, 10:16 AM UTC

cwmoore wrote: post #407

echelon wrote: post #268

Earlier quoted context omitted.

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.

Are those oil derricks, or wind turbines? Who cares! Graphic design is easy now!

[dead]

Re: Gemini 2.5 Flash Image

#499

Post by jrran086 » Sat, Aug 30, 2025, 5:58 PM UTC

[dead]

Re: Gemini 2.5 Flash Image

#500

Post by gitaarik » Mon, Sep 01, 2025, 10:29 AM UTC

I added a picture of myself as an attachment and asked it to put me in a professional dev environment. Worked very good and was also very funny. Then I asked it to put me in a scene where I'm meeting Frank Zappa in his studio. Then it gave an error with "Content blocked, Content not permitted". Interesting..