25 skills found
ByteDance-Seed / SeedVRRepo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)
IceClear / SeedVR2[ICLR2026] SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
IDKiro / SdxsSDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
THU-SI / VideoScene[CVPR 2025 Highlight] VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
Guaishou74851 / AdcSR(CVPR 2025) Adversarial Diffusion Compression for Real-World Image Super-Resolution [PyTorch]
jkwang28 / OSDFaceOfficial Repo for CVPR 2025 paper "OSDFace: One-Step Diffusion Model for Face Restoration"
Zeqiang-Lai / OpenDMDOpen source implementation and models of One-step Diffusion with Distribution Matching Distillation
mingukkang / ElatentlpipsAuthor's Implementation for E-LatentLPIPS
zhengchen1999 / DOVE[NeurIPS'25] DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution
vivoCameraResearch / Any To Bokeh[ICLR2026] Any-to-Bokeh is a novel one-step video bokeh framework that converts arbitrary input videos into temporally coherent, depth-aware bokeh effects.
DSL-Lab / MoFlow[CVPR 2025] MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation Distillation
VinAIResearch / SwiftBrushSwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation (CVPR 2024)
jp-guo / CODiff[ICCV'25] Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal
yuanzhi-zhu / SlimFlow[ECCV2024] "SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow", Yuanzhi Zhu, Xingchao Liu, Qiang Liu
yuanzhi-zhu / DiMO[ICCV2025] "Di[M]O: Distilling Masked Diffusion Models into One-step Generator", Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière, Vicky Kalogeiton
vivoCameraResearch / AdaRefSRAdaRefSR is a novel reference-based one-step diffusion super-resolution framework. Paper was accepted by ICLR2026.
SYZhang0805 / DisBackThe official implementation of Distribution Backtracking Distillation for One-step Diffusion Models
vaskers5 / LUAOne Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Model
Zyriix / D2OOfficial implemention for Diffusion Models Are Innate One-Step Generators
zhengchen1999 / SODEC[AAAI'26] Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression
