Generative AI art refers to artworks created with the help of Generative Artificial Intelligence models. These models are designed to generate new content, such as images, music, text, or even 3D models, based on prompts. 

Over at CRITICA Singapore, we use local runtime Stable Diffusion Automatic1111 (Stability AI) ComfyUI for Generative AI. Below are some images of some Generative AI we have done in our studio.

Generative AI art is an intersection of art and technology, where the creative process involves the collaboration between human artists and machine learning algorithms.

Key characteristics of generative AI art include:

Creation: Stable Diffusion Automatic1111 is a generative artificial intelligence model that produces unique photorealistic images from text and image prompts.

Inspiration and Assistance: Generative AI can serve as a valuable tool for artists, providing inspiration and assisting them in exploring new artistic directions and styles.

Custom Training Model: AI models can be trained on diverse datasets encompassing various aesthetics, empowering them to adeptly employ a multitude of artistic styles across different contexts.

Extraction of Poses from Stills/Videos: It is able to detect and track the human body in from a reference and can accurately estimate the pose of the body in 3D space.

Prompt engineering is an iterative process that involves experimenting with different prompts and fine-tuning them to achieve the desired outcomes from the AI model. It requires a good understanding of the AI model’s capabilities and limitations and creative thinking to design prompts that elicit the desired responses.