CG Virtual Influencer

Use Case: Creation of a AI human, with custom photography styles, pose, environments, facial expressions, hair detail, makeup, wardrobe,etc. We can input any face & train using Machine Learning. (We generated these using Stable Diffusion A1111.) Midjourney will not be able to achieve such custom results.

Trixie.Jade23

Trixie is our custom generated personality in Stable Diffusion Automatic1111. Below are examples of the visual consistency of the character.

We can control her expression, yet maintaining temporal consistency.

Different locations, outfits.

Other characters

Older Generations

Stable Diffusion is a latent diffusion model, a kind of deep generative artificial neural network.

The development of Stable Diffusion was funded and shaped by the start-up company Stability AI. The technical license for the model was released by the CompVis group at Ludwig Maximilian University of Munich. Development was led by Patrick Esser of Runway and Robin Rombach of CompVis, who were among the researchers who had earlier invented the latent diffusion model architecture used by Stable Diffusion.

More detailed workflow explanation here.