Seonglae ChoDue to the nature of AI, it will first replace fields of art where accuracy is not crucial, and this is already happening. It was expected that art and humanities would be the last to be replaced, but the opposite is true. However, just as AI in chess didn't kill the Go market, there will consistently be demand for human-created art.
AI Arts
Dataset
metmuseum/openaccess · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
https://huggingface.co/datasets/metmuseum/openaccess
This startup is setting a DALL-E 2-like AI free, consequences be damned
DALL-E 2, OpenAI's powerful text-to-image AI system, can create photos in the style of cartoonists, 19th century daguerreotypists, stop-motion animators and more. But it has an important, artificial limitation: a filter that prevents it from creating images depicting public figures and content deemed too toxic.
https://techcrunch.com/2022/08/12/a-startup-wants-to-democratize-the-tech-behind-dall-e-2-consequences-be-damned
This AI art app is a glimpse at the future of synthetic media
If you've been hanging out on Twitter lately, then you've probably noticed a profusion of AI-generated images sprouting all over your timeline like weird, algorithmic visions. These pictures have been generated using a new app called Dream, which lets anyone create "AI-powered paintings" by simply typing a brief description of what they want to see.
https://www.theverge.com/2021/12/6/22820106/ai-art-app-dream-synthetic-media-wombo
Alien Dreams: An Emerging Art Scene
In January 2021, OpenAI released the weights and code for their CLIP model, and since then various hackers, artists, researchers, and deep learning enthusiasts have figured out novel methods for combining CLIP with various generative models to create beautiful visual art from just a text prompt.
https://ml.berkeley.edu/blog/posts/clip-art/?utm_source=tldrnewsletter
VQGAN+CLIP - How does it work?
The synthetic imagery ("GAN Art") scene has recently seen a kind of productivity explosion: A new kind of neural network architecture capable of generating images from text was quickly popularized through a freely available Google Colab notebook. It enabled thousands of people to create stunning/fantastic/magical images, just by inputting a text prompt.
https://alexasteinbruck.medium.com/vqgan-clip-how-does-it-work-210a5dca5e52
TikTok now offers a very basic text-to-image AI generator directly in the app
Text-to-image AI systems are booming in both ability and popularity right now, and what better proof than their appearance in the world's hottest app: TikTok. The video platform recently added a new effect it calls "AI greenscreen" that allows users to type in a text prompt that the software will then generate as an image.
https://www.theverge.com/2022/8/15/23306101/tiktok-ai-greenscreen-filter-text-to-image-mainstream
