News for hackers. Stuff that matters.
Re:Illustrating Gutenberg library using Stable Diffusion by naillo on Sunday September 04, 2022 @11:20AM (#32714001)
Is this really using stable diffusion? Has a really 'midjourney' type style to it.
Re:Illustrating Gutenberg library using Stable Diffusion by Aedraie on Sunday September 04, 2022 @12:02PM (#32714420)
Good eyes! We currently pipe text input to Stable Diffusion, Dall-E and Midjourney at the same time and continue with the most pleasing result. The (very small compared to what we want to achieve) content we currently have required hundreds of renderings and Midjourney came out as most pleasing nearly all of the times. From what's on the website only the Sherlock Holmes renderings have been produced using Stable Diffusion. Nothing published so far from Dall-E, which most of the times is showing us uncanny valley. In terms of preference: We are experimenting hard to achieve better results using Stable Diffusion.
Re:Illustrating Gutenberg library using Stable Diffusion by Tenobrus on Sunday September 04, 2022 @02:43PM (#32716304)
I find stable diffusion requires a lot more prompt engineering than either midjourney or dalle, but has a higher ceiling of quality if you do put in that effort. I wouldn't expect just using exactly the same prompt for all three models would work very well, need at least a little tuning per-model.
Re:Illustrating Gutenberg library using Stable Diffusion by poisonarena on Sunday September 04, 2022 @12:11PM (#32714511)
If the majority of the models were produced with Midjourney, why did you title it as SD as u did?
Re:Illustrating Gutenberg library using Stable Diffusion by dqpb on Sunday September 04, 2022 @12:27PM (#32714724)
Probably easier to get on the front page since Stable Diffusion is trending.
Re:Illustrating Gutenberg library using Stable Diffusion by qzw on Sunday September 04, 2022 @12:42PM (#32714883)
The sad thing is that they could’ve also put Midjourney (and DALL-E) in the title and not lost any votes.
Re:Illustrating Gutenberg library using Stable Diffusion by cal85 on Sunday September 04, 2022 @01:39PM (#32715558)
Why sad?
Re:Illustrating Gutenberg library using Stable Diffusion by fsloth on Sunday September 04, 2022 @12:08PM (#32714485)
With this effort it sounds it would be faster to actually draw the frames yourself. Get exactly what you want and so on…
Re:Illustrating Gutenberg library using Stable Diffusion by johnfn on Sunday September 04, 2022 @12:21PM (#32714655)
Of course, then you have to learn how to draw, which can take years and years for middling results (source: me)
Re:Illustrating Gutenberg library using Stable Diffusion by spyder on Sunday September 04, 2022 @03:32PM (#32716824)
Or in between the two: draw just some blobs to set the general concept and do img2img with diffusion models.

https://simonwillison.net/2022/Aug/29/stable-diffusion/

Re:Illustrating Gutenberg library using Stable Diffusion by karencarits on Sunday September 04, 2022 @12:18PM (#32714612)
One interesting feature of these services is that one can be surprised: suddenly you get an image that is different from what you envisioned when writing the prompt but that is still visually pleasing or interesting or inspiring
Re:Illustrating Gutenberg library using Stable Diffusion by samstave on Sunday September 04, 2022 @12:51PM (#32715020)
>>what we want to achieve

What is it, SPECIFICALLY, you want to achieve.

And, assuming you do achieve THING, what are the negative consequences of such achievement?

How will you be accountable for dark patterns?

What recourse would any biologically physical Human Being have against [THE BAD THING] that may ensue from said achievements...

SERIOUS QUESTION

Re:Illustrating Gutenberg library using Stable Diffusion by samstave on Sunday September 04, 2022 @05:18PM (#32717817)
You literally can't fucking answer this question?
Re:Illustrating Gutenberg library using Stable Diffusion by cercatrova on Sunday September 04, 2022 @12:58PM (#32715119)
Midjourney now used SD underneath