top of page

Vignettes of a Lost World : New Delhi 2222

An exercise in Visual Development and Worldbuilding
Made using SD 1.5, Photoshop and Premiere Pro (Predating the release of contemporary video diffusion models such as Stability AI's Stable Video Diffusion and OpenAI's Sora)

Vignettes of a Lost World | New Delhi 2222
Play Video

The above video was created stacking several Low Rank Adaptation Models (LoRA) to generate unique images.

The resulting images (displayed below) were then exported into Premiere pro where I animated them to achieve a parallax effect.

This was made possible using the Node Network I set up in Houdini (as seen in the image on the right) using the Stable Houdini Plugin.

Screenshot 2024-06-14 194616.png
bottom of page