stylegan
gpt-2
stylegan | gpt-2 | |
---|---|---|
31 | 64 | |
13,945 | 21,146 | |
0.3% | 1.1% | |
0.0 | 2.5 | |
23 days ago | 25 days ago | |
Python | Python | |
GNU General Public License v3.0 or later | 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.
stylegan
-
An AI artist isn't an artist
Been following generative AI since 2017 when nvidia released their first GAN paper & the results always fascinated me. Trained my own models with their repo then experimented with other open source projects. went thru the pain of assembling my own data set, tweaking code parameters to achieve what i'm looking for, had to deal with all kinds of hardware/software issues. I know it's not easy. (screenshot of a motorbike GAN model i was training in 2018 https://imgur.com/a/SIULFhR, was taken after 5 hours of training on a gtx 1080) or this, cinema camera output from another locally trained model. So yeah i have a couple ideas of how generative AI works. yup things were that bad few years ago, that technology has come a long way. Using & setting up something like stable diffusion with automatic1111 webui isn't really a complex process. Though generating AI art locally is always gonna feel more rewarding than using a cloud based service.
-
Clearview AI scraped 30 billion images from Facebook and gave them to cops: it puts everyone into a 'perpetual police line-up'
Their algorithm is public, you could do it yourself if you have the proper hardware: https://github.com/NVlabs/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]
- This was taken outdoors with no special lighting
-
What the F**k
Jokes aside, ML moves extremely fast and our field is quickly advancing. The honest truth is that no researcher can even keep up other than their extremely niche corner. I'll show you an example. Here's what state of the art image generation looked like in 2014, 2018, and here is today (which now is highly controllable using text prompts instead of data prompts).
- Garfield
-
Teaching AI to Generate New Pokemon
The fundamental technology we will use in this work is a generative adversarial network. Specifically, the Style GAN variant.
-
A100 vs A6000 vs 3090 for computer vision and FP32/FP64
Based on my findings, we don't really need FP64 unless it's for certain medical applications. But The Best GPUs for Deep Learning in 2020 — An In-depth Analysis is suggesting A100 outperforms A6000 ~50% in DL. Also the Stylegan project GitHub - NVlabs/stylegan: StyleGAN - Official TensorFlow Implementation uses NVIDIA DGX-1 with 8 Tesla V100 16G(Fp32=15TFLOPS) to train dataset of high-res 1024*1024 images, I'm getting a bit uncertain if my specific tasks would require FP64 since my dataset is also high-res images. If not, can I assume A6000*5(total 120G) could provide similar results for StyleGan?
-
[D] Which gpu should I choose?
Yes that's what I thought. But StyleGan https://github.com/NVlabs/stylegan uses NVIDIA DGX-1 with 8 Tesla V100 16G GPUs(FP32=15) to do the training, not sure if it's related to its high-res training images or something else.
gpt-2
-
What are LLMs? An intro into AI, models, tokens, parameters, weights, quantization and more
Medium models: Roughly between 1B to 10B parameters. This is where Mistral 7B, Phi-3, Gemma from Google DeepMind, and wizardlm2 sit. Fun fact: GPT 2 was a medium sized model, much smaller than its latest versions.
- Sam Altman is still trying to return as OpenAI CEO
- Build Personal ChatGPT Using Your Data
-
Are the recent advancements in AI technology primarily driven by recent discoveries or the progress in hardware capabilities and the abundance of available data?
"Our model, called GPT-2 (a successor to GPT), was trained simply to predict the next word in 40GB of Internet text. Due to our concerns about malicious applications of the technology, we are not releasing the trained model. As an experiment in responsible disclosure, we are instead releasing a much smaller model for researchers to experiment with, as well as a technical paper. "
-
BING IS NOW THE DEFAULT SEARCH FOR CHATGPT
They did release GPT-2 under the MIT License.
-
Don Knuth Plays with ChatGPT
Did you arrive at this certainty through reading something other than what OpenAI has published? The document [0] that describes the training data for GPT-2 makes this assertion hilarious to me.
[0]: https://github.com/openai/gpt-2/blob/master/model_card.md#da...
- Was frustriert euch an der Nutzung oder der Diskussion um KI?
- The AI
-
Help with pet project to learn - Running ChatGPT-2 at home
I made a clone of https://github.com/openai/gpt-2 on my local laptop
- По поводу опасности ИИ и предложений остановить разработки на 6 месяцев.
What are some alternatives?
pix2pix - Image-to-image translation with conditional adversarial nets
dalle-mini - DALL·E Mini - Generate images from a text prompt
stylegan2 - StyleGAN2 - Official TensorFlow Implementation
minGPT - A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
lucid-sonic-dreams
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time
DeOldify - A Deep Learning based project for colorizing and restoring old images (and video!)
gpt-neo - An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
aphantasia - CLIP + FFT/DWT/RGB = text to image/video
sentencepiece - Unsupervised text tokenizer for Neural Network-based text generation.
ffhq-dataset - Flickr-Faces-HQ Dataset (FFHQ)
jukebox - Code for the paper "Jukebox: A Generative Model for Music"