News for hackers. Stuff that matters.
Re:Stable Diffusion 2.0 and the Importance of Negative Promp... by lelandfe on Monday November 28, 2022 @11:15PM (#33783618)
Yeah – I tested these sorts of "bad image" negative prompts a lot in 1.5 and found they had almost no impact whatsoever. It may be different in 2.0, like the tweet author says, but it is also pretty telling that in that tweet they're using "blurry", "blurred", and "grainy" and are rendering images with heavily blurred backgrounds and obvious film grain.

Very specific, normal keywords like "amputated" may have a positive impact, though. Hard to tell. Doing apples-to-apples comparisons with negative keywords is challenging because even a single extra keyword tends to completely change the image.

One thing that SD really impressed me by, though, is its understanding of symmetry. "Symmetrical composition" is an incredibly powerful phrase: https://imgur.com/a/lioJ8ak

And it does, indeed, extend to anatomy as well – "symmetrical eyes" can help a lot, while "symmetrical arms" renders people with their arms raised or outstretched.

Re:Stable Diffusion 2.0 and the Importance of Negative Promp... by astrange on Monday November 28, 2022 @11:37PM (#33783748)
Symmetry is effective for compression, so that makes sense - when messing with NovelAI I actually couldn't get it to generate asymmetrical hairstyles like Lain's.
Re:Stable Diffusion 2.0 and the Importance of Negative Promp... by Agentlien on Tuesday November 29, 2022 @01:19AM (#33784259)
I did some tests on SD 1.5 with certain challenging prompts such as gymnasts doing a handstand. Using no negative prompt they became amorphous blobs. I'm guessing because gymnasts are often in dynamic poses which are hard for SD to understand.

I decided to add a negative prompt. With a bit of experimentation I realised all the "bad" had no effect. However, "blob" actually made most of the deformities go away and "amputee" did help against partial limbs being generated.

Something that worked even better was replacing "gymnast" with "athletic man"/"athletic woman" in the positive prompt.

Re:Stable Diffusion 2.0 and the Importance of Negative Promp... by visarga on Tuesday November 29, 2022 @03:13AM (#33784916)
Welcome to the latent space where you can add, subtract and operate on words like they are mathematical objects. I suppose people are going to intuitively learn how the latent space works by exercising prompts.
Re:Stable Diffusion 2.0 and the Importance of Negative Promp... by Nition on Tuesday November 29, 2022 @02:59AM (#33784826)
I wonder how much better these models would be if they were exactly the same, but the training images all had accurate, detailed descriptions.
Re:Stable Diffusion 2.0 and the Importance of Negative Promp... by sdenton4 on Friday December 02, 2022 @01:27AM (#33827504)
Train a captioning system, generate the captions, then train the image generator...