I've been using the 256x256 HD Rivershavewings notebook, and it does take a remarkably long time, but it's a more resource-intensive process than VQGAN. I'm pretty sure a less resource-intensive notebook using the same underlying architecture would produce much less accurate results. I find the diffusion notebook more than worth the wait, honestly; I've gotten some incredible results using it. 256x256 is definitely small, but I upscale my outputs using an ESRGAN notebook by @jotakrevs. Successful prompt engineering for diffusion is different than for VQGAN+Clip, too. Just by feel alone, I'd say VQGAN feels more like sculpting with words/poetry and Diffusion feels more like building/architecture. I don't know if that makes sense.
You are viewing a single comment's thread from:
Thx for your answer. I think we are indeed aligned. If i find alternative useful resources, i'll share it.
Please do!!!
You both had an interesting talk here! I cannot access the notebook due permissions... maybe you shared the link that only works with people you add to the list.
Diffusion, first time I hear about. I'm eager to test this stuff 😛
Here's a link to the tweet announcing the notebook! That should work for you :)
I think you'll really love Clip-Guided Diffusion. It produces more realistic/accurate results than VQGAN+Clip, and diffusion models outperform GANs in general, as well :)
Oh yay thanks! I'll check it later!
Hi @jotakrevs, @kaliyuga, @castleberry, @lavista ... Maybe you already knew but i just found this playground :
https://replicate.ai/explore
Hi @dbddv01. This seems really interesting. There are so many models to try out. And I didn’t know about this. Thank you so much for sharing this. Maybe @eve66 and @kitzune will be interested in it too.
Cool, thanks for the mention @lavista . This is an interesting topic and actually i've been thinking about this lately :) Helpful post @dbddv01 . Thanks
This looks to be very interesting. I am gonna have to look around at this and see what there is to see. Who doesn't love a little playtime at the right playground?! Thanks for caring and sharing and nice find!
Hi @jotakrevs. First off, sorry to butt in like this in this comment thread. I have seen amazing pictures of clip guided diffusion by RiversHaveWings on her twitter feed. Just look at those images and you'll be tempted to try it out. Thank you @kaliyuga for posting the links to the notebooks. I too will check it out later.
This is for those who have Colab Pro, needs 16 GB of video memory :
@kaliyuga thanks a lot, I'll try it soon, got busy with my current AI artworks.
@dbddv01 oh, that looks interesting, I'll take a look, thanks!
@lavista wow, 512 sounds better than 256... I have the cheap account of Colab Pro, so I get usually T4 GPU, that is not enough, and time to time P100. I'll try this notebook when I get a P100. Don't need to say sorry, I was the first one to butt in in this chat hehe.
Regards to all!
@dbddv01 @lavista @jotakrevs @castleberry I just created a Hive community for AI art and technique discussion because I found this conversation and a few similar ones so fun.
Just joined. Thank you.
Here is the link... i joined yesterday! Thanks for thinking of us!
https://peakd.com/c/hive-177949/created
Awesome:) just joined it too!
Cool!