One of the services of Cognitive Camvas is our own version of Stable Diffusion which is a superset of the publicly available version.
You can send prompts through our service API during live minting to get images and save them with the metadata for each customized live mint.
Some of the extra features include:
- Choose the model version, including 1.5.
- Negative Prompt: Specify aspects of the image to remove.
- Attention/Emphasis: () in the prompt increases the model's attention to enclosed words, and [] decreases it.
- Weighted Prompts: Use weights for specific words in your prompt to change their importance, e.g. red:2.4 dragon:1.2.
Artist Conditioned Models
Another very interesting feature we are including is the ability of select artists to condition the Stable Diffusion model with their own artworks. This will produce images in the style of the conditioned images.
Of course, only the artist will be able to produce images with this conditioned model.
This has some amazing benefits, the least of which is discovering how other types of art will look with the conditioned style.
Maybe you are an artist who produces abstract art and would like to see how the style would look generating cityscapes or landscapes. Now you can find out.
We think this is one of the most overlooked features of AI. Most artists will make amazing discoveries using a conditioned model, and it could open entire new areas of exploration.