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

21–30 of 241 posts

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

#21

Post by TekMol »

midlightdenight wrote: post #10
ilaksh wrote: post #6

Does anyone know if there is something like Google Cloud for GPUs but with an easy way to suspend the VM or container when not in use? Maybe I am just looking for container hosting with GPUs. I am just trying to avoid some of the basic VM admin stuff like creating, starting, stopping for SaaS if someone already has a way to do. Maybe this is something like what Elastic Beanstalk does.

Maybe not quite what you’re looking for, but I’ve seen some people mention banana.dev https://www.banana.dev/ Never used it myself, but looks like AWS Lambda/GCP Cloud Functions tailored to ML models.

"Log in with Github". No thanks.

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

#22

Post by bryced »

kumarm wrote: post #17
bryced wrote: post #14

Earlier quoted context omitted.

Works fine for me, you just need to adjust the strength of the edit.

You mean steps?

For the specific example you provide you could also use a prompt-based mask to prevent it from editing the person.

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

#24

Post by malux85 »

TekMol wrote: post #8

How can I try this? Can this be run on a Digitalocean VM? I looked around on DO's products, but none seems to advertise that it has a GPU. So maybe it is not possible?

Try paperspace, they have GPUs and you can set billing limits to stop accidental overusage

(no affiliation other than being a happy customer)

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

#25

Post by punkspider »

ilaksh wrote: post #6

Does anyone know if there is something like Google Cloud for GPUs but with an easy way to suspend the VM or container when not in use? Maybe I am just looking for container hosting with GPUs. I am just trying to avoid some of the basic VM admin stuff like creating, starting, stopping for SaaS if someone already has a way to do. Maybe this is something like what Elastic Beanstalk does.

I think there's https://brev.dev and https://banana.dev

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

#27

Post by do_anh_tu »

nullish_signal wrote: post #3

>11GB VRAM Aaarrrgghh let me know when it's down to 4GB like Stable Diffusion The prompt-based masking sounds incredible, with either pixel +/- or Prompt Relevance +/- VERY impressive img2img capabilities!

Or, if there is a Colab version, I’d happy to pay Google for premium GPU.

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

#28

Post by Uehreka »

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 expecting to develop a long-lasting business around hand-cranking people's cars for them when they fail to start.

Like, come on. We're now seeing AIs take on tasks many people thought would never be doable by machine. And granted, many people (myself included to some extent) have adjusted their priors properly. And yet so many people act like AI is going to stall in its current lane and leave room for human work as opposed to developing orders of magnitudes better intelligence and obliterating all of its current flaws.

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

#29

Post by chadcmulligan »

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…

Haven't we been here before? - see self driving cars.

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

#30

Post by cududa »

chadcmulligan wrote: post #29
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…

Haven't we been here before? - see self driving cars.

No.
Post reply on HN