This is really cool. Haven't seen something like this yet. Going to be very interesting when you start to see E2E generation => animation/video/static => post editing => repeat. Have this feeling that movie studios are going to look into this kind of stuff. We went from real to CGI and this could take it to new levels in cost savings or possibilities.
Show HN: New AI edits images based on text instructions
181–190 of 241 posts
Re: Show HN: New AI edits images based on text instructions
#182Wow this is cool I think I am going to make a site so people can use this
Re: Show HN: New AI edits images based on text instructions
#183Here is a colab you can try it in. It crashed for me the first time but worked the second time. https://colab.research.google.com/drive/1rOvQNs0Cmn_yU1bKWjC...
EDIT - it's free of charge: https://research.google.com/colaboratory/faq.html
---
First time I've used "colab" - looks great. Out of interest, who pays for the compute used by this?
Is it freely offerred by Google? Or is it charged to my Google API account when I use it? Or your account? It wasn't clear in the UI.
Re: Show HN: New AI edits images based on text instructions
#184I see it's able to generate politician faces. I recall this wasn't possible on DALL·E 2 due to safety restrictions.
I run a friendly caption contest https://caption.me so imaginAIry is going to be absolute gold for generating funny and topical content. Thank you @bryced!
Re: Show HN: New AI edits images based on text instructions
#185What are the most affordable GPUs that will run this? (it said it needs CUDA, min 11GB VRAM, so I guess my relatively puny 4GB 570RX isn't going to cut it!)
On the strength of this HN submission I just ordered an RTX 3060 12GB card for £381 on Amazon so I can run this and future AI models.
This stuff is fascinating, and @bryced's imaginAIry project made it accessible to people like me who never had any formal training in machine learning.
Re: Show HN: New AI edits images based on text instructions
#186This is really cool. Haven't seen something like this yet. Going to be very interesting when you start to see E2E generation => animation/video/static => post editing => repeat. Have this feeling that movie studios are going to look into this kind of stuff. We went from real to CGI and this could take it to new levels in cost savings or possibilities.
Played around for a bit. Definitely a cool tool. Wish I had an M1 though. Taking me quite a bit to generate and fans running at full blast. Haha
Re: Show HN: New AI edits images based on text instructions
#187Earlier 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.
But it requires transmission over the internet, right? This is actually very interesting. Am I legally allowed to draw naked kids for my own enjoyment in the comfort of my own home?
Simple possession is also a crime, just a state crime. The internet transmission triggers federal jurisdiction and federal charges. There is no safe/legal way to possess such images.
Re: Show HN: New AI edits images based on text instructions
#188Earlier quoted context omitted.
"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.
I guess we should lower our standards, then...
Re: Show HN: New AI edits images based on text instructions
#189The language of high-level art-direction can be way more complex than one might assume. I wonder how this model might cope with the following: ‘Decrease high-frequency features of background.’ ‘Increase intra-contrast of middle ground to foreground.’ ‘Increase global saturation contrast.’ ‘Increase hue spread of greens.’
They behave quite poorly, because the keywords used by the models are layman language not technical art or color correction/color grading-speak Hopefully in a couple of years when things have matured more there will be more models capable of handling said requests The most precise models are actually anime models because the users have got high standards for telling the machine what they expect of it and the database…
Around how many samples are required for an effective training set?
Re: Show HN: New AI edits images based on text instructions
#190I've been toying with SD for a while, and I do want to make a nice and clean business out of it. It's more of a side-projecty thing so to speak.
Our "cluster" is running on a ASUS ROG 2080Ti external GPU in the razer core-x housing, and that actually works just fine in my flat.
We went through several iterations of how this could work at scale. The initial premise was basically the google homepage, but for images.
That's when we realised that scaling this to serve the planet was going go be a hell of a lot more work. But not really, conceptualising the concurrent compute requirements as well as the ever-changing landscape and pace of innovation in this absolutely necessary.
The quick fix is to use a message queue (we're using Bull) and make everything asynchronous.
So essentially, we solved the scaling factor using just one GPU. You'll get your requested image, but it's in a queue, we'll let you know when it's done. With that compute model in place, we can just add more GPUs, and tickets will take less time to serve if the scale engineering is proper.
I'm no expert on GPU/Machine learning/GAN stuff but Stable Diffusion actually prompted me to imagine how to build and scale such a service, and I did so. It is not live yet, but when it does become so the name reserved is dreamcreator dot ai, and I can't say when it will be animated. Hopefully this year.