- Video/Image ... Vision ... Enhancement ... Fake ... Reconstruction ... Colorize ... Occlusions ... Predict image ... Image/Video Transfer Learning ... Art ... Photography
- End-to-End Speech ... Synthesize Speech ... Speech Recognition ... Music
- Humor ... Writing/Publishing ... Storytelling ... Broadcast ... Journalism/News ... Podcasts ... Books, Radio & Movies - Exploring Possibilities
- Teaching Machines to Draw | David Ha - Google
- Neural Synesthesia - exploring the possibilities of immersive, digital media
- The US Copyright Office says an AI can’t copyright its art | Adi Robertson - The Verge
- The Weird and Wonderful World of AI Art
- AI won an art contest, and artists are furious | Rachel Metz - CNN
- Artist uses AI to extract color palettes from text descriptions | Benj Edwards - ARS Technica
New technologies, and in particular artificial intelligence, are drastically changing the nature of creative processes. Computers are playing very significant roles in creative activities such as music, architecture, fine arts, and science. Indeed, the computer is already a canvas, a brush, a musical instrument, and so on. However, we believe that we must aim at more ambitious relations between computers and creativity. Rather than just seeing the computer as a tool to help human creators, we could see it as a creative entity in its own right. This view has triggered a new subfield of Artificial Intelligence called Computational Creativity. Artificial Intelligence and the Arts: Toward Computational Creativity | Ramón López de Mántaras - Article from the book The Next Step: Exponential Life - OpenMind BBVA
Can AI Create Visual Arts?
Stable Diffusion with ControlNet
- Stable Diffusion | Stability AI
- Adding Conditional Control to Text-to-Image Diffusion Models | L. Zhang, A. Rao, & M. Agrawala - arXiv
So how does it work? We've covered Stable Diffusion frequently before. It's a neural network model trained on millions of images scraped from the Internet. But the key here is ControlNet, which first appeared in a research paper titled "Adding Conditional Control to Text-to-Image Diffusion Models" by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala in February 2023, and quickly became popular in the Stable Diffusion community. Typically, a Stable Diffusion image is created using a text prompt (called text2image) or an image prompt (img2img). ControlNet introduces additional guidance that can take the form of extracted information from a source image, including pose detection, depth mapping, normal mapping, edge detection, and much more. Using ControlNet, someone generating AI artwork can much more closely replicate the shape or pose of a subject in an image. - Funky AI-generated spiraling medieval village captivates social media | Benj Edwards - ARS Technical ... "This was the point where AI-generated art passed the Turing Test for me."
an online experimental platform that uses machine learning to turn your scribbles into manga illustrations. It uses a suite of AI and machine learning tools — trained by over 140,000 high-res images — to transform your doodle into the protagonist of a doujinshi.
starryai is an AI art generator app. You simply enter a text prompt and Starryai transforms your words into works of art. Generate art 🎨 simply by describing what you want to see -- your words into art. Starryai
Web-based app – start from a text prompt. Generate, tweak and download up to 2 artworks per day for free. NightCafe lets you generate art using either VQGAN+CLIP (”Artistic”) or CLIP-Guided Diffusion (”Coherent”). NightCafe
Web-based app – several intriguing tools. Start with the ‘Pro-Art Filters’ to apply filters to your uploaded photo, or go a bit deeper to train an AI to create new pictures based on stuff you upload PlayForm
A collection of web-based AI tools to create, personalize, enlarge, sharpen, and more. PlayForm
- The Big Sleep
- CLIP + Guided Diffusion 512x512
- Quick Guided Diffusion
- Disco Diffusion
- ruDALLE arbitrary resolution v2.0
- pixray Getting Started Notebook
Recurrent Neural Network (RNN) & Art
Recurrent Neural Networks (RNNs) have found applications in various fields, including art, where they are used to create, analyze, and enhance various forms of artistic content. Here are some ways RNNs are used in the realm of art:
- Generating Artistic Text: RNNs can be trained on large text corpora, including literature, poetry, and other forms of written art, to generate text that mimics the style and tone of famous authors or poets. This is often referred to as "text generation" or "text completion."
- Generating Visual Art: RNNs can be used to generate visual art, such as paintings or drawings. Artists and researchers have trained RNNs on databases of existing artwork to create new pieces of art that capture certain styles or themes. For instance, the style transfer technique uses RNNs to blend the styles of different artworks.
- Image and Video Processing: RNNs are used for various image and video processing tasks in the art domain. For instance, they can be used for image captioning, where the network generates textual descriptions of images. They can also be used for video generation, manipulation, and enhancement.
- Artistic Style Transfer: Style transfer techniques, often using variants of RNNs, allow artists and creators to apply the artistic style of one image to another. This can lead to visually appealing and unique artistic effects.
- Interactive Art Installations: RNNs can be employed in interactive art installations, where they analyze input from sensors, cameras, or other sources and generate responsive and dynamic artistic content. This can create immersive and engaging experiences for viewers or participants.
- Art Critique and Analysis: RNNs and other neural network models can be used to analyze and critique artworks based on various parameters, such as composition, color usage, and style. This can help artists and art enthusiasts gain insights into the artistic qualities of a piece.
- Art Restoration and Preservation: RNNs can assist in the restoration and preservation of art by helping to reconstruct damaged or faded artwork based on existing fragments and historical data.
- Art Market Predictions: RNNs, along with other machine learning techniques, can be used to analyze trends in the art market, predict future art market developments, and assist collectors and investors in making informed decisions.