AI and creative work

AI and creative work

After the appearance of all those AI tools that allow generating images from prompts, the next obvious question is how they integrate into the creative workflow for visual artists. Will those artists be replaced by AI? How does their work change? In which form?

This post shows nicely the possibilities how to start with a simple line-drawing and the use stable diffusion from an AI model (composed of about 4.2G of weights) in order to produce great images. Some manual fine tuning using Gimp or Photoshop may still be required:

If you want to try it yourself you can find the model and instructions at Github:

Disclaimer of the authors (same source):

While commercial use is permitted under the terms of the license, we do not recommend using the provided weights for services or products without additional safety mechanisms and considerations, since there are known limitations and biases of the weights, and research on safe and ethical deployment of general text-to-image models is an ongoing effort. The weights are research artifacts and should be treated as such.