[HN Gopher] Generative AI Image Editing Showdown
___________________________________________________________________
Generative AI Image Editing Showdown
Author : gaws
Score : 63 points
Date : 2025-10-28 20:58 UTC (2 hours ago)
(HTM) web link (genai-showdown.specr.net)
(TXT) w3m dump (genai-showdown.specr.net)
| joomla199 wrote:
| Good effort, somewhat marred by poor prompting. Passing in "the
| tower in the image is leaning to the right," for example, is a
| big mistake. That context is already in the image, and passing
| that as a prompt will only make the model apt to lean the tower
| in the result.
| minimaxir wrote:
| Everyone is sleeping on Gemini 2.5 Flash Image / Nano Banana. As
| shown in the OP, it's substantially more powerful than most other
| models while at the same price-per-image, and due to its text
| encoder it can handle _significantly_ larger and more nuanced
| prompts to get exactly what you want. I open-sourced a Python
| package for generating from it with examples
| (https://github.com/minimaxir/gemimg) and am currently working on
| a blog post with even more representative examples. Google also
| allows generations for free with aspect ratio control in AI
| Studio: https://aistudio.google.com/prompts/new_chat
|
| That said, I am surprised Seedream 4.0 beat it in these tests.
| herval wrote:
| Gemini is great when it gets it right, but in my experience, it
| sometimes gives you completely unexpected results and won't get
| it right no matter what. You can see that in some of the
| examples (eg the Girl with the pearl earring one). I'm
| constantly surprised by how good Flux is, but the tragedy is
| most people (me included) will just default to whatever they
| normally use (chatgpt and gemini, in my case), so it doesn't
| really matter that it's better
| daemonologist wrote:
| I don't think people are really sleeping on it - nano-banana
| more or less went viral when it first came out. I'd argue that
| aside from the capabilities built into ChatGPT (with the Ghibli
| craze and whatnot) craze it's the best known image editing
| model.
| cosama wrote:
| I was trying to use gemini 2.5 flash image / nano banana to
| tidy up a picture of my messy kitchen. It failed horribly on my
| first attempt. I was quite surprised how much trouble it had
| with this simple task (similar to cleaning up the street in the
| post). On my second attempt I had it first analyze the image to
| point out all the items that clutter the space, and then on a
| second prompt had it remove all those items. That worked much
| better, showing how important prompt engineering is.
| hackthemack wrote:
| I do not use ai image generating much lately. It seemed like
| there was a burst of activity a year and half ago with self
| hosted models and using some localhost web guis. But now it seems
| like it is moving more and more to online hosted models.
|
| Still, to my eye, ai generated images still feel a bit off when
| doing with real world photographs.
|
| George's hair, for example, looks over the top, or brushed on.
|
| The tree added to the sleeping person on the ground photo... the
| tree looks plastic or too homogenized.
| minimaxir wrote:
| > But now it seems like it is moving more and more to online
| hosted models.
|
| It's mostly because image model size and required compute for
| both training and inference have grown faster than self-hosted
| compute capability for hobbyists. Sure, you can run Flux
| Kontext locally, but if you have to use a heavily quantized
| model and wait forever for the generation to actually run, the
| economics are harder to justify. That's not counting the "you
| can generate images from ChatGPT for free" factor.
|
| > George's hair, for example, looks over the top, or brushed
| on.
|
| IMO, the judge was being too generous with the passes for that
| test. The only one that really passes is Gemini 2.5 Flash
| Image:
|
| Flux Kontext: In addition to the hair looking too slick, it
| does not match the VHS-esque color grading of the image.
|
| Qwen-Image-Edit: The hair is too slick and the
| sharpness/saturation of the face unnecessarily increases.
|
| Seedream 4: Color grading of the entire image changes, which is
| the case with most of the Seedream 4 edits shown in this post,
| and why I don't like it.
| jimmyl02 wrote:
| I think reve (https://reve.com) should be in the running and
| would be very curious to see the results!
| keyle wrote:
| This was fun.
|
| Some might critique the prompts and say this or that would have
| done better, but they were the kind of prompt your dad would type
| in not knowing how to push the right buttons.
| lxe wrote:
| This is vastly more useful than benchmark charts.
|
| I've been using Nano Banana quite a lot, and I know that it
| absolutely struggles at exterior architecture and landscaping.
| Getting it to add or remove things like curbs, walkways, gutters,
| etc, or to ask to match colors is almost futile.
| estetlinus wrote:
| I am trying Qwen Image Edit for turning day photos into night,
| mostly architecture etc. Most models are struggling, and Nano
| Banana misses edges and stuff, making the pictures align
| poorly.
| kgwgk wrote:
| Recent discussion: https://news.ycombinator.com/item?id=45708795
___________________________________________________________________
(page generated 2025-10-28 23:00 UTC)