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

Show HN: New AI edits images based on text instructions

github.com

Post reply on HN
Print view View original

171–180 of 241 posts

Re: Show HN: New AI edits images based on text instructions

#171

Post by wongarsu »

babarock wrote: post #156
sandworm101 wrote: post #115

Earlier quoted context omitted.

Nudity isnt really the core issue. It is about illegal content. Nudity is the over-protective, over-inclusive bandaid solution to prevent this thing from being used to generate the very illegal material that will trigger authorities.

Genuinely curious what type of content would be considered illegal here. - the tool is drawing original content. - the tool is executing on my laptop. - the output image is not shared with anyone. In a way, whatever this tool can do, MS Paint could (theoretically) do. Or am I misunderstanding the whole thing?

There's a great wikipedia page on this very topic [1]. In some countries like Germany fictional porn isn't considered porn, while other countries like Australia or France consider the possession of drawings of naked minors a crime worthy of jail sentences. And then there's the US where having the images on a computer is fine, as long as they aren't sent over the internet and the computer never crosses state lines.

In general it's a topic people are careful about because the legal situation is complex, and in many countries associated with the potential of heavy jail sentences.

1: https://en.wikipedia.org/wiki/Legal_status_of_fictional_porn...

Re: Show HN: New AI edits images based on text instructions

#172

Post by lobocinza »

bryced wrote: post #42
Uehreka wrote: post #28

It's a little premature, fine, but I want to start liquidating my rhetorical swaps here: I've been saying since last summer (sometimes on HN, sometimes elsewhere) that "prompt engineering" is BS and that in a world where AI gets better and better, expecting to develop lasting competency in an area of AI-adjacent performance (a.k.a. telling an AI what to do in exactly the right way to get the right result) is akin to…

Been doing a lot with prompts lately. What people are calling "prompt engineering" I'd call "knowing what to even ask for and also asking for it in a clear manner". That was a valuable skill before computers and will continue to be one as AI progresses. I've been pretty disappointed to introduce ChatGPT to people in jobs where it would be a game changer and they just don't know what to do with it. They ask it for not…

Most people struggle with deliberate logical thought.

Re: Show HN: New AI edits images based on text instructions

#173

Post by wongarsu »

kleiba wrote: post #164
sandworm101 wrote: post #158

Earlier quoted context omitted.

Nope. It is illegal if you do it on ms paint too. Images of naked kids (real or fiction) + transmitted over internet (ie state lines) = bad bad day for all involved.

> + transmitted over internet (ie state lines) But OP specifically said: "the tool is executing on my laptop. - the output image is not shared with anyone."

Maybe use a desktop instead, because crossing state lines with that laptop might carry a jail sentence with a minimum term of 5 years.

Re: Show HN: New AI edits images based on text instructions

#175

Post by dang »

bryced wrote: post #170
Damirakyan wrote: post #168

Earlier quoted context omitted.

How would I upgrade to 2.1 if running locally?

If you're wanting to use Stable Diffusion 2.1 with imaginairy you just specify the model with `--model SD-2.1` when running the `aimg imagine` command.

Sorry for the offtopicness but could you please email me at hn@ycombinator.com? (I have an idea/possibility for you. Nothing that couldn't be posted here in principle but I'd rather not take the thread off topic.)

Re: Show HN: New AI edits images based on text instructions

#176

Post by wongarsu »

TeMPOraL wrote: post #89

> Here are some examples of transformations it can make: Golden gate bridge: I'm on mobile so can't try this myself now. Can it add a Klingon bird of prey flying under the Golden Gate Bridge, and will "add a Klingon bird of prey flying under the Golden Gate Bridge" prompt/command be enough?

No. At least not with the Stable Diffusion 1.5 checkpoint used in the colab notebook. It seems to only have a very vague idea of what a Klingon bird of prey is. The best I could get in ~30 images was [1], and that's with slight prompt tweaks and a negative prompt to discourage falcons and eagles.

1: https://i.imgur.com/gDj2Kn4.png

Re: Show HN: New AI edits images based on text instructions

#177

Post by bryced »

perfopt wrote: post #75
bryced wrote: post #64

Earlier quoted context omitted.

Shouldn't be downloads per prompt. Processing happens on your machine. It does download models as needed. A network call per prompt would be a bug.

I keep seeing this even when the prompt is unchanged Downloading https://huggingface.co/runwayml/stable-diffusion-v1-5/resolv... from huggingface Loading model /home/hrishi/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/889b629140e71758e1e0006e355c331a5744b4bf/v1-5-pruned-emaonly.ckpt onto cuda backend... followed by a download

Oh I see what you're saying. It's not actually downloading but there is a bug where it's not using the cache properly. will fix

Re: Show HN: New AI edits images based on text instructions

#178

Post by c7b »

cma wrote: post #134
c7b wrote: post #90

Earlier quoted context omitted.

Dreambooth is what I'm using now, but I think I remember the concept had a specific name, something like 'context transfer' or so (pretty sure that was not the term) and tools that were pretty good at it that came out before Dreambooth. If I could at least remember the term it might be easier to search for them. Dreambooth is ok at it, but it requires multiple images (you often read 30, but I've actually had decent r…

"textual inversion"

I think that's it, thank you!

Re: Show HN: New AI edits images based on text instructions

#179

Post by brycedriesenga »

bryced wrote: post #15
PaulMest wrote: post #7

I've played with several of these Stable Diffusion frameworks and followed many tutorials and imaginAIry fit my workflow the best. I actually wrote Bryce a thank you email in December after I made an advent calendar for my wife. Super excited to see continued development here to make this approachable to people who are familiar with Python, but don't want to deal with a lot of the overhead of building and configuring…

Thanks Paul!

Whoa. Another Bryce D. So when do we fight?

Re: Show HN: New AI edits images based on text instructions

#180

Post by aflag »

sfpotter wrote: post #144
aflag wrote: post #133

Earlier quoted context omitted.

I'm not an artist, but they look fine to me. I am not the kind of person who spends hours in a Gallery admiring the nuances of paintings or photos. However, at the level of detail I usually admire these things, the clown one looked interesting and the Monalisa one was funny. The strawberry seemed a bit weird, but I don't think I'd care for it even if it was perfect anyway. The wintery landscape I thought was pretty g…

"I'm not qualified to have a nuanced opinion about this, but let me confidently tell you what I think..."

Well, most people who consume art are not professional artists. That was my main point. From the point of view of a lay person (such as I), it looks pretty good.
Post reply on HN