Picture for Tiankai Hang

Tiankai Hang

Improved Noise Schedule for Diffusion Training

Add code
Jul 03, 2024
Figure 1 for Improved Noise Schedule for Diffusion Training
Figure 2 for Improved Noise Schedule for Diffusion Training
Figure 3 for Improved Noise Schedule for Diffusion Training
Figure 4 for Improved Noise Schedule for Diffusion Training
Viaarxiv icon

Step-aware Preference Optimization: Aligning Preference with Denoising Performance at Each Step

Add code
Jun 06, 2024
Viaarxiv icon

Simplified Diffusion Schrödinger Bridge

Add code
Mar 27, 2024
Figure 1 for Simplified Diffusion Schrödinger Bridge
Figure 2 for Simplified Diffusion Schrödinger Bridge
Figure 3 for Simplified Diffusion Schrödinger Bridge
Figure 4 for Simplified Diffusion Schrödinger Bridge
Viaarxiv icon

CCA: Collaborative Competitive Agents for Image Editing

Add code
Jan 23, 2024
Viaarxiv icon

InstructDiffusion: A Generalist Modeling Interface for Vision Tasks

Add code
Sep 07, 2023
Figure 1 for InstructDiffusion: A Generalist Modeling Interface for Vision Tasks
Figure 2 for InstructDiffusion: A Generalist Modeling Interface for Vision Tasks
Figure 3 for InstructDiffusion: A Generalist Modeling Interface for Vision Tasks
Figure 4 for InstructDiffusion: A Generalist Modeling Interface for Vision Tasks
Viaarxiv icon

Efficient Diffusion Training via Min-SNR Weighting Strategy

Add code
Mar 22, 2023
Figure 1 for Efficient Diffusion Training via Min-SNR Weighting Strategy
Figure 2 for Efficient Diffusion Training via Min-SNR Weighting Strategy
Figure 3 for Efficient Diffusion Training via Min-SNR Weighting Strategy
Figure 4 for Efficient Diffusion Training via Min-SNR Weighting Strategy
Viaarxiv icon

Language-Guided Face Animation by Recurrent StyleGAN-based Generator

Add code
Aug 11, 2022
Figure 1 for Language-Guided Face Animation by Recurrent StyleGAN-based Generator
Figure 2 for Language-Guided Face Animation by Recurrent StyleGAN-based Generator
Figure 3 for Language-Guided Face Animation by Recurrent StyleGAN-based Generator
Figure 4 for Language-Guided Face Animation by Recurrent StyleGAN-based Generator
Viaarxiv icon

Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions

Add code
Nov 19, 2021
Figure 1 for Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions
Figure 2 for Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions
Figure 3 for Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions
Figure 4 for Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions
Viaarxiv icon