alt Hacker NewsCoarse Is Better
Comments
I'm no image gen expert but these prompts are downright terrible even by my standards.
Are you really complaining that ", from the British Museum." leads to it a painting in the actual British Museum? Just remove the sentence, and you'll be fine. Now good luck trying to make Midjourney place the image at the museum!
I'm a paying MJ user and am impressed by Nano Banana. They're different models. They each serve their purpose.
This analysis is just noise. Yawn.
Ironically, even an LLM with its fake reasoning capabilities can point out the issue with the prompts if you ask it to critique this article.
Eno applies:
> It's the sound of failure: so much modern art is the sound of things going out of control, of a medium pushing to its limits and breaking apart. The distorted guitar sound is the sound of something too loud for the medium supposed to carry it. The blues singer with the cracked voice is the sound of an emotional cry too powerful for the throat that releases it. The excitement of grainy film, of bleached-out black and white, is the excitement of witnessing events too momentous for the medium assigned to record them.
The author is using special prompts exploiting flaws of the old models, and doesn't like that new models interpret the hacks literally instead.
The new models have prompt adherence precise enough to distinguish what "British Museum" or "auction at Christie's" is from the art itself, instead of blending a bag of words together into a single vector and implicitly copying all of the features of all works containing "museum" or "ArtStation" in their description.
The author's prompts are fighting against what Nano Banana was optimized for. Saying "British Museum" to MJv2 worked because it blurred all images tagged with museums into the aesthetic. NBP interprets it literally: show me something IN a museum.
This isn't worse - it's different. MJv2 was a happy accident machine. NBP is a precision tool.
If you want the coarse aesthetic, prompt for it: "rough brushstrokes, visible canvas texture, unfinished edges, painterly, loose composition". NBP will give you exactly that because it actually understands what you're asking for.
The real lesson: we're in a transition period where prompting strategies that exploited old model quirks no longer work. That's fine - we just need to adapt our prompting to match what the model was designed to do.
Years of refinement on the taste of people with no taste has produced a model with no taste. Crazy
You’re definitely on to something, people wouldn’t criticize as much as they are otherwise, they’d ignore it.
I think the whole point is that in optimizing for instruction following and boring realism we’ve lost what could have been some unique artistic elements of a new medium, but anyway.
While I don’t disagree with the author, these are simply two completely different tools with different use cases. Nano Banana Pro throws out fantastic images you can actually use in your marketing right away. It’s not an art tool - it’s a business tool
As long as the older tools still exist to make art, I don’t see what the problem is. Use NBP to make your marketing pics, MJv2 for your art
The problem is not in the image models rather the training data and its context. "British museum" for MJ is the image source, "British museum" is the setting for Nano Banana.
I love the inherent wonder and joy in this post around the original images.
AI doesn’t make art. The OP is trying to fit the square peg of their intuitive understanding about the art creation process into the round hole of generating it via AI
I don’t see splashes of primary color as more artistic. Anyway, what if you just ask it “more coarse”? I see impressive depth in the latest outputs, but as with all technically proficient performers, you might just have to consciously scale it back.
Is some kind of MoE or routing (but for image models obviously), depending on the prompt ask, a possible solve?
The OP would likely prefer Disco Diffusion if they want their art to remain coarse. Modern models possess advanced spatial understanding and adhere strictly to prompts, whereas the OP is using unstructured inputs better suited for older models with CLIP or T5 encoders that lack that spatial awareness. These legacy prompting styles are incompatible with Gen3 models that utilize VLMs as text encoders. If the OP wants to explore modern architecture, they should use Flux.2 with a LoRA or perhaps a coarser model like Zit if they prefer to rely solely on text conditioning. Nano Banana Pro requires extremely long and distinctive prompting to achieve specific aesthetics. His blog post shows a lack of understanding and a lack of adaption to modern architecture which would be fine if it wasn't that dismissive.
Here is an image from NBP with an adapted prompt for Italian futurism: https://imgur.com/a/4pN0I0R
and for Kowloon:
Another word for coarse is impasto technique, where the paint is so thick the painting-knife or brush strokes are visible and leave a pronounced texture (e.g. Van Gogh, Rembrandt).
Another cool prompt could be specific painting techniques (e.g. pencil shading, glaze) as if you were training an actual artist in a specific technique.
Just fucking by canvas, brushes and good quality oil paint. You need only five colours[1]. Cost you maybe 50-80 euros. And any mess you produce will give you more joy thanand shot produced by any clanker brain. Keep at it for few years, take evening classrs, look tutorials and you have learned yourself a skill. You can now travel to any majos art museum across the world and have a discussion with masters through their works hanging on the wall.
And you will also see how fucking sad and inferior all these ai images are. Really, trust me, please. There is more to art than this. There is more to life.
The author claims the old models are better at creating art than the new ones. I disagree; art requires consciousness and intent while this type of model is capable of neither.
[dead]
[dead]
[dead]
[flagged]
It's ridiculous lol.
Midjourney is optimized for beautiful images, while Nano Banana is optimized for better prompt adherence and (more importantly) image editing. It should be obvious for anyone who spent 20 minutes trying out these models.
If your goal is to replace human designers with cheaper options[0], Nano Banana / ChatGPT is indefinitely more useful than Midjourney. I'd argue Midjourney is completely useless except for social media clout or making concept art for experienced designers.
[0]: A hideous goal, I know. But we shouldn't sugarcoat it: this is what underpin the whole AI scheme now.