DeOldify
stylegan
Our great sponsors
DeOldify | stylegan | |
---|---|---|
58 | 31 | |
17,561 | 13,924 | |
- | 0.4% | |
2.7 | 0.0 | |
7 months ago | 8 days ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
DeOldify
- Is there a way to colorize images like this using controlNet and without morphing his face? If yes, does anyone know how?
- ControlNet for Automatic1111 is here!
-
I improved the colorization of the NYC 1911 film by combining multiple colorization neural networks. Here is a brief comparison to the previous method. I will leave a link to the full video in the comments for those who are interested.
The old method is simple. All you need to do is running DeOldify with a colab notebook. Then you can pick any neural networks you want for upscale and frame interpolation. A lot of people use dain-app, but I find rife faster and easier to use.
- Anyone know of a (preferably local) batch-image colourisation software?
-
Retro personal computer ads from the 1980s
I think the novel and interesting tech is still happening, its just that without the colorful ads for it on TV, and without the software being packaged up and sold with pretty box art that you can physically hold, it doesn't feel as much like a capital-E Experience. It's probably the Internet's fault that we don't do things like that anymore, but the upside is that we now have access to so many ideas and applications from all over, even ones that aren't commercially viable.
Some that look exciting to me are: an AI that lets you animate still photos realistically [1], a simple website that guides you to discover new parks, eateries, and other places near you [2], an AI that colorizes old black-and-white photos/video [3], a Street View style map of the game world from "The Legend of Zelda: Breath of the Wild", with some 1st person 360 degree photos [4], and a tiny game engine that lets you distribute your whole game physically via printed QR codes [5].
If marketing and graphic design people ever felt like getting together to do some 'side projects', I vote that they should make print ads for apps/websites that they like :)
[1] https://github.com/AliaksandrSiarohin/first-order-model
[2] https://randomlocation.xyz (https://randomlocation.xyz/help.txt for customization)
[3] https://github.com/jantic/DeOldify
-
Kennedy VS Nixon, Part One (1960) | 4k | HFR | COLORIZED | ANIMATED.
Thank you. Photo-restore + Deoldify + Animegan + Rife + 4K upscale
- Estou a colorir vídeos antigos que estão em B/W usando as GPU's do trabalho. Encontrei a primeira visita de Franco a Lisboa em 1949. O áudio está em português, os únicos filmes a cores que encontrei neste momento são do documentario no DMAX em espanhol. Quase nada de Portugal.
-
Reconstruct a face from multiple old photos of the same person? At different ages?
DeOldify
- Video restoration AI
-
[D] Should expert opinion be a bigger part of the Machine Learning world?
I don't know if that's a great example of the benefits of domain experts for ML. She specifically cherrypicked images which are themselves extremely unusual for old photographs (and you've probably seen them shared on social media before precisely because they are such colorful pioneering color photographs, with a level of quality & detail that wouldn't become common in color photography for a long time afterwards). And the point about minimizing average error tending to make for conservative image choices rather than sampling from the distribution is an old one which is familiar to anyone with the most passing interest in NN colorization - if you look up the (now 3-4-year-old) library used, Antic's DeOldify, his discussion is pretty much all about how to fight the averaging using GAN techniques which encourage the colorization model to at least pick a mode and get nice bright colors that way while minimizing GAN use as much as possible (because GANs are miserable to train). You don't need a Twitter 🧵 lecturing you on this deep insight, everyone is already well-aware of that the first time they train a decolorizer and go "why is it so brown".
stylegan
-
StyleGAN-T Nvidia, 30x Faster than SD?
Umm, StyleGAN was the first decent image generation model, and it was producing great images from random seeds 5 years ago. Now, that's with the obvious caveat that each model was trained to produce one specific type of image and it helped immensely if the training images were all aligned the same. Diffusion models are certainly the trendy current architecture for image generation, but AFAIK there's no fundamental theoretical limitation to the output quality of any architecture except the general rule that more parameters is better.
- The Concept Art Association updates their AI-restricting gofundme campaign, revealing their lack of AI understanding & nefarious plans! [detailed breakdown]
-
[1812.04948] A Style-Based Generator Architecture for Generative Adversarial Networks
PDF link Landing page
-
Innovative Technology NVIDIA StyleGAN2
Code: https://github.com/NVlabs/stylegan
https://arxiv.org/abs/1812.04948 (A Style-Based Generator Architecture for Generative Adversarial Networks)
-
Technoalchemy - a short spiritual book combining GPT-3 text and art made with StyleGAN + other ML techniques
Check out the PDF here I've been calling this "the first spiritual guidebook written by an AI". The text was written almost entirely with GPT-3, minus the couple of paragraphs I wrote as prompt. The art was made with various tools - for instance, the cover was made in part with Aphantasia (CLIP+FFT), the title page is an old public domain photo colorized with DeOldify, the faces made with StyleGAN, both standalone and via Artbreeder. Let me know what you think - I have a couple bigger projects building off of the techniques I used, and I would appreciate any feedback!
-
[Hobby Scuffles] Week of March 21, 2021
stylegan this is the tech behind all those "this ___ does not exist" sites. it's actually surprisingly easy to use if you know how to use the terminal (and preferably a little bit of python).
-
NEW PYTHON PACKAGE: Sync GAN Art to Music with "Lucid Sonic Dreams"!
Clone stylegan
What are some alternatives?
pix2pix - Image-to-image translation with conditional adversarial nets
stylegan2 - StyleGAN2 - Official TensorFlow Implementation
sd-webui-controlnet - WebUI extension for ControlNet
Real-ESRGAN-ncnn-vulkan - NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.
ArtLine - A Deep Learning based project for creating line art portraits.
cnn-colorize - CNN Model to Colorize Grayscale Images
lucid-sonic-dreams
colorize-photos - Colorize all the photos in a directory
aphantasia - CLIP + FFT/DWT/RGB = text to image/video
colorize - Colorize black and white photos.
colornet-template - Colorizing B&W Photos with Neural Networks