Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)
-
Updated
Jan 27, 2026 - Python
Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)
[ICLR2026] SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
(CVPR 2025) Adversarial Diffusion Compression for Real-World Image Super-Resolution [PyTorch]
Author's Implementation for E-LatentLPIPS
Any-to-Bokeh is a novel one-step video bokeh framework that converts arbitrary input videos into temporally coherent, depth-aware bokeh effects.
[CVPR 2025] MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation Distillation
Add a description, image, and links to the one-step-diffusion-model topic page so that developers can more easily learn about it.
To associate your repository with the one-step-diffusion-model topic, visit your repo's landing page and select "manage topics."