DiffusionLight: Light Probes for Free by Painting a Chrome Ball

1 code implementation • 14 Dec 2023 • Pakkapon Phongthawee, Worameth Chinchuthakun, Nontaphat Sinsunthithet, Amit Raj, Varun Jampani, Pramook Khungurn, Supasorn Suwajanakorn

To address this problem, we leverage diffusion models trained on billions of standard images to render a chrome ball into the input image.

Lighting Estimation

Talking Head(?) Anime from a Single Image 4: Improved Model and Its Distillation

no code implementations • 29 Nov 2023 • Pramook Khungurn

We study the problem of creating a character model that can be controlled in real time from a single image of an anime character.

Diffusion Sampling with Momentum for Mitigating Divergence Artifacts

1 code implementation • 20 Jul 2023 • Suttisak Wizadwongsa, Worameth Chinchuthakun, Pramook Khungurn, Amit Raj, Supasorn Suwajanakorn

The first technique involves the incorporation of Heavy Ball (HB) momentum, a well-known technique for improving optimization, into existing diffusion numerical methods to expand their stability regions.

Text-to-Image Generation