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

Opendream: A layer-based UI for Stable Diffusion

github.com

Post reply on HN
Print view View original

21–30 of 158 posts

Re: Opendream: A layer-based UI for Stable Diffusion

#22

Post by stale2002 »

coding123 wrote: post #15
joemi wrote: post #13

Earlier quoted context omitted.

Doesn't this entirely depend both on what its been trained on and what style is being output? But also, philosophically, is it even "theft" to make something in-the-style-of someone? I believe these questions and their complex answers are the reason you've been downvoted.

I understand why the person was downvoted, but not why the person was flagged. It doesn't make sense for someone to flag "AI art is theft." Downvotes because you didn't back up what you mean. Flagged because there are AI fanboys that want to sensor speech perhaps?

I would say that it absolutely deserved to be flagged because it was a comment of little engagement.

It both isn't directly related to the original post, and also didn't even make any particular arguments. It was just a 5 word declaration of fact, that is borderline offtopic.

Re: Opendream: A layer-based UI for Stable Diffusion

#27

Post by michaelt »

Zetobal wrote: post #4
cwkoss wrote: post #2

Very cool. Would be interesting to train a model on images with alpha channels so outputs would be automatically masked and more easily composable. But maybe masking is so good these days that would be futile? When a user does img-2-img on a layer does it use the context from other visible layers in the generation?

Segmentation is solved... https://github.com/RockeyCoss/Prompt-Segment-Anything

Segment Anything is neat, but segmentation is far from solved.

If the user generates a picture of a horse and rider to add onto another composition - they probably want to include the saddle.

Re: Opendream: A layer-based UI for Stable Diffusion

#28

Post by GaggiX »

michaelt wrote: post #27
Zetobal wrote: post #4

Earlier quoted context omitted.

Segmentation is solved... https://github.com/RockeyCoss/Prompt-Segment-Anything

Segment Anything is neat, but segmentation is far from solved. If the user generates a picture of a horse and rider to add onto another composition - they probably want to include the saddle.

SAM is also conditioned on points, if it's ambiguous what you want to mask you can add a point on the saddle and the model will add it without a problem, segmentation is pretty much solved, I agree with the parent post.
Post reply on HN