ECCV 2026 paper: x0-prediction tackles high-dimensional latent diffusion
An ECCV 2026 paper studies the diffusability of representation autoencoder (RAE) latent spaces, showing that fine-tuning encoders for reconstruction lowers effective dimensionality, and that x0-prediction outperforms velocity prediction for high-dimensional latent diffusion, improving text-to-image generation.
2026-09-24 ~ 2026-09-24 · 2 related posts
- x0-prediction beats velocity in high-dim RAE latents, boosting text-to-image diffusion — Chao Feng · 2026-09-24
- ECCV 2026 paper: x0-prediction fixes inefficient diffusion in reconstruction-tuned RAE latent spaces — serrjoa · 2026-09-24