Photo credit: Stelfie
Paradox-free time travel is believed to be possible by some researchers, but one man just couldn’t wait, so he decided to use Stable Diffusion AI to take selfies both in the past and future. More specifically, Stable Diffusion 1.5 that was trained on the fictional ‘Stelfie’ character and then lots of in-painting was used to fix errors and faces. Each image that you’re about to see took around 3-hours to generate.
The Stable Diffusion model basically supports the ability to create new images from scratch through the use of a text prompt describing elements to be included or omitted from the output. Or, you can re-draw existing images to incorporate new elements described by a text prompt, otherwise known as “guided image synthesis”, through its diffusion-denoising mechanism. For those wanting to try it out, it’s recommended that Stable Diffusion be run on a system with 10GB or more VRAM.
- Powerful Productivity: 11th Generation Intel Core i3-1115G4 Dual Core processor delivers unmatched speed and intelligence, enabling impressive...
- Visibly Stunning: Experience sharp details and crisp colors on the 15.6" Full HD IPS display with 82.58% screen-to-body, 16:9 aspect ratio and narrow...
- Ergonomic Typing: Ergonomically-designed hinge lifts the keyboard for comfortable typing, improved cooling, and a better sound experience