Drag Your GAN Explained: Image Editing via Drag & Drop Using AI | Paper Reimplementation | Tutorial

  Рет қаралды 2,552

Martin Thissen

Martin Thissen

Күн бұрын

Пікірлер: 30
@martin-thissen
@martin-thissen Жыл бұрын
The official code has been released now, you can find it here: github.com/XingangPan/DragGAN/tree/main
@anaanab
@anaanab Жыл бұрын
will u post a video on how to install and run it?
@kennette2121
@kennette2121 Жыл бұрын
yeah man, you are one of the best out there so far that I've found! Super interested in the AI space although I am super busy with my primary job as a more full stack developer. Your videos keep the content clear and help me keep up with all the rapid movements in the space! Keep it up !
@letianwang5141
@letianwang5141 Жыл бұрын
awsome video! Both technical and understandable!
@Omnificuser
@Omnificuser Жыл бұрын
Keep going bro you have been a huge inspo for me!
@74Gee
@74Gee Жыл бұрын
So glad you're back!!
@martin-thissen
@martin-thissen Жыл бұрын
Thanks, happy to here I was missed! :-)
@t.b.5493
@t.b.5493 Жыл бұрын
Awesome video! Continue like that!
@martin-thissen
@martin-thissen Жыл бұрын
Thanks a lot! :-)
@Fredi-yu3rc
@Fredi-yu3rc Жыл бұрын
Love your videos! Could you make a video about the RedPajama-INCITE models?
@martin-thissen
@martin-thissen Жыл бұрын
Thanks so much! I will add it to my list. :)
@sidarth404
@sidarth404 Жыл бұрын
Can you please solve the colab tortoise problem " To access the website, please confirm the tunnel creator's public IP below." that you provided.
@74Gee
@74Gee Жыл бұрын
I'm wondering if an interface that overlays a point mesh would significantly slow down the image generation. So using depth estimation to create the mesh and then a 3D package to manipulate the mesh to create the pixel vectors. When that is then passed to the image generation, would say 30 points have a 30 times increase in actually generating the image? Or would it have a similar generation time? My thinking is the point mesh could be more easily constrained to the form of the subject (face, body etc) as for these example the constraints are well known. The benefit of this would be the ability to drag say a nose out of bounds and it would manipulate the entire mesh to remain within bounds, maybe to turn the entire head. I suspect that adding multiple drag vectors would have some effect on generation time but possibly not. What do you think?
@martin-thissen
@martin-thissen Жыл бұрын
Yes, the more points you add the longer does the optimization of the intermediate latent w take. Actually the authors did exactly what you described in their paper and in their shown example it worked really well. Have a look at figure 7 in the paper if you want :) vcai.mpi-inf.mpg.de/projects/DragGAN/data/paper.pdf
@74Gee
@74Gee Жыл бұрын
@@martin-thissen Thanks that's an interesting paper. I should have read that first!
@velo1337
@velo1337 Жыл бұрын
when will you release a llama 2 video?
@martin-thissen
@martin-thissen Жыл бұрын
Appreciate that you're asking, just uploaded the video: kzbin.info/www/bejne/jaumhGuwbqykftk Hope you like it :-)
@Fredi-yu3rc
@Fredi-yu3rc Жыл бұрын
Is there a discord server for this channel? if not it would be great to have one!
@martin-thissen
@martin-thissen Жыл бұрын
I haven't created one yet, but am planning to do create one soon :)
@Fredi-yu3rc
@Fredi-yu3rc Жыл бұрын
@@martin-thissen That would be so great so people can help each other etc
@deeprajmajumdar1423
@deeprajmajumdar1423 4 ай бұрын
how to place custom images of our own? and use that in this model?
@martin-thissen
@martin-thissen 4 ай бұрын
Unfortunately, this is a little more complicated, but it can be done using GAN inversion: arxiv.org/pdf/2101.05278
@deeprajmajumdar1423
@deeprajmajumdar1423 4 ай бұрын
@@martin-thissen would you create a video for that thanks in advance ☺️
@DeeprajMajumdarM23CSE012
@DeeprajMajumdarM23CSE012 4 ай бұрын
@@martin-thissen Yes sir! Waiting for a video.
@bgNinjashows
@bgNinjashows Жыл бұрын
KZbin algorithm is brutal my dude took some time off and algorithm definitely did not like that. Geez
@martin-thissen
@martin-thissen Жыл бұрын
Looks like that haha. But I will recover from it! :)
@bgNinjashows
@bgNinjashows Жыл бұрын
@@martin-thissen 😀
@williamstrickland6892
@williamstrickland6892 Жыл бұрын
😴 Promo>SM
@leemark7739
@leemark7739 Жыл бұрын
Not official implement.by the way can we process our own image
@martin-thissen
@martin-thissen Жыл бұрын
Yes, mentioned that in the video as well. The official code got released now: github.com/XingangPan/DragGAN/tree/main Yes, for this you need GAN inversion.
龟兔赛跑:好可爱的小乌龟#short #angel #clown
01:00
Super Beauty team
Рет қаралды 129 МЛН
Mia Boyka х Карен Акопян | ЧТО БЫЛО ДАЛЬШЕ?
1:21:14
Что было дальше?
Рет қаралды 9 МЛН
1, 2, 3, 4, 5, 6, 7, 8, 9 🙈⚽️
00:46
Celine Dept
Рет қаралды 69 МЛН
Amazing remote control#devil  #lilith #funny #shorts
00:30
Devil Lilith
Рет қаралды 11 МЛН
Diffusion Models | Paper Explanation | Math Explained
33:27
Outlier
Рет қаралды 257 М.
Create Cinematic AI Videos with Pika Labs
11:30
Curious Refuge
Рет қаралды 288 М.
67 Minecraft Things That Are Totally Broken
29:14
Skip the Tutorial
Рет қаралды 4,1 МЛН
AI Learns to Walk (deep reinforcement learning)
8:40
AI Warehouse
Рет қаралды 9 МЛН
How Stable Diffusion Works (AI Image Generation)
30:21
Gonkee
Рет қаралды 155 М.
AI Learns To Swing Like Spiderman
15:29
b2studios
Рет қаралды 6 МЛН
How AIs, like ChatGPT, Learn
8:55
CGP Grey
Рет қаралды 10 МЛН
A.I. Learns to Drive From Scratch in Trackmania
16:51
Yosh
Рет қаралды 7 МЛН
Why Are Open Source Alternatives So Bad?
13:06
Eric Murphy
Рет қаралды 669 М.
龟兔赛跑:好可爱的小乌龟#short #angel #clown
01:00
Super Beauty team
Рет қаралды 129 МЛН