Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Using “underdrawings” for accurate text and numbers

samcollins.blog

Post reply on HN
Print view View original

131–140 of 140 posts

Re: Using “underdrawings” for accurate text and numbers

#131

Post by mrec »

HotHotLava wrote: post #81
ErroneousBosh wrote: post #79

Earlier quoted context omitted.

I wonder how long it took to come up with all this? Because if I wanted a spiral of little "buttons" like the last one at the end (and they don't look very much like sweets) I'd be able to knock that out in Blender in an afternoon, and I'm not very good at Blender.

I think you're vastly overestimating the average persons ability to use Blender if you can do that in an afternoon; just figuring out how to place a colored cube and the camera probably takes an afternoon if you pick up Blender for the first time.

Yeah, I've bounced off Blender twice now. And I've written a (basic) 3D modeller.

I think part of the problem is that pretty much all the tutorial material for Blender seems to be in video form, which is easily my least effective way to learn, even leaving aside the "I've only got one screen" issue.

Re: Using “underdrawings” for accurate text and numbers

#133

Post by IdiotSavage »

vunderba wrote: post #123
ryanthedev wrote: post #82

Earlier quoted context omitted.

I believe most detailed prompts are AI generated.

This is 100% true. There are entire nodes/pipelines in programs like ComfyUI that are designed to take a simple prompt and "enhance it" which usually involves making it more verbose, adding detail, etc depending on the target model. Original Prompt: "Man with Trapezoid Head" AI Expansion: Portrait of a man with a trapezoid-shaped head, sharp geometric facial structure, angular jawline wider at the top and narrowing t…

Yes, this is exactly the kind of prompt I often see. Then you have stuff like "8k resolution". WTF? The output is fixed anyway.

Re: Using “underdrawings” for accurate text and numbers

#134

Post by ErroneousBosh »

sebastianmestre wrote: post #116
Brendinooo wrote: post #90

Earlier quoted context omitted.

I remember opening Blender for the first time years ago and thinking it had the steepest learning curve of any software I'd ever used.

It's not perfect, but it's been vastly improved in recent years. If you lost interest in 3D art because of Blender's bad UX in the past, I recommend you give it another shot. Also, there might be other new 3D software with better UX. I am not a Blender fanboy, but I do love 3D art and graphics programming and want as many people as possible to get into it :^)

Yeah somewhere between 2 and 3 it got a very much improved UI.

Re: Using “underdrawings” for accurate text and numbers

#135

Post by mncharity »

barbazoo wrote: post #129

I've had a lot of success at work breaking down tasks that are supposed to be "done by the agent" into small LLM calls orchestrated deterministically via boring queues and messages. That's why this really resonates with me in a world where we're lured deep into the ecosystem by the model vendors. At the end of the day we can get so much done just by breaking down a problem into smaller problems.

> deterministically

But won't it be fun when we can cloud burst-parallel a grid/tiled sampling of multiple code implementations/architectures, and interactively explore navigate/blend-points-in the latent design space. Multiples embodying different trade-offs, styles, clarity vs performance, etc. Code as generative art. What might the software engineering equivalent of designer moodboards be?

Re: Using “underdrawings” for accurate text and numbers

#136

Post by sailorganymede »

I run an art training app and one of the features I am working on is AI generated critique (it's an app for training realism.) And I noticed if I gave the AI the original image, the tonal breakdown of the image the app generates as well as the user's drawing, it delivered critique far better and more targeted.

Re: Using “underdrawings” for accurate text and numbers

#137

Post by usagisushi »

Geonode wrote: post #60

We've been doing this for a long time now, it's similar to using a depth map or a line drawing to control the silhouette.

Yeah, I’ve used a similar technique to build a "pizza clock" before (where the number of slices corresponds to the hours).

Re: Using “underdrawings” for accurate text and numbers

#138

Post by sebastianmestre »

ErroneousBosh wrote: post #134
sebastianmestre wrote: post #116

Earlier quoted context omitted.

It's not perfect, but it's been vastly improved in recent years. If you lost interest in 3D art because of Blender's bad UX in the past, I recommend you give it another shot. Also, there might be other new 3D software with better UX. I am not a Blender fanboy, but I do love 3D art and graphics programming and want as many people as possible to get into it :^)

Yeah somewhere between 2 and 3 it got a very much improved UI.

I think 2.8 is where the Blender Foundation showed their commitment to improving the UX, but it just continually kept going from there

Re: Using “underdrawings” for accurate text and numbers

#139

Post by barbazoo »

mncharity wrote: post #135
barbazoo wrote: post #129

I've had a lot of success at work breaking down tasks that are supposed to be "done by the agent" into small LLM calls orchestrated deterministically via boring queues and messages. That's why this really resonates with me in a world where we're lured deep into the ecosystem by the model vendors. At the end of the day we can get so much done just by breaking down a problem into smaller problems.

> deterministically But won't it be fun when we can cloud burst-parallel a grid /tiled sampling of multiple code implementations/architectures, and interactively explore navigate/blend-points-in the latent design space. Multiples embodying different trade-offs, styles, clarity vs performance, etc. Code as generative art. What might the software engineering equivalent of designer moodboards be?

I guess that would be cool.

Re: Using “underdrawings” for accurate text and numbers

#140

Post by nicbou »

IdiotSavage wrote: post #61

> Transform this image into a photographed claymation diorama of assorted artisan chocolates and candies […] viewed from a low-angle Side note: whenever I read prompts for image generation, I notice very specific details which the model obviously ignored. Here the chocolates / candies in the last two images look anything but artisanal. They look very "sterile" and mass-produced. The viewing angle is also not accurate…

There might be an overlap between people who use AI enough to write such posts, and people who don’t respect craftsmanship. The output looks fine to them because they never trained their eye to look closer. They vaguely hear music but never listen to the notes.
Post reply on HN