PROJECT

LTX-2.5 Video Restoration and Depixelation

Fine-tunes a frozen LTX-2.5 video model with rank-64 LoRA on FFHQ and COCO restoration trajectories. The completed FFHQ run improved four metrics on 10 held-out faces, while a one-image COCO check showed mixed signals: better LPIPS and MS-SSIM, but worse pixel-error metrics. Broader restoration quality and identity preservation remain unproven.

Training diagnostics from the 5,000-step FFHQ full-restoration run.
PROJECTS UPDATES