Picture for Liangbin Xie

Liangbin Xie

Image Conductor: Precision Control for Interactive Video Synthesis

Add code
Jun 21, 2024
Viaarxiv icon

SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models

Add code
Dec 11, 2023
Figure 1 for SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models
Figure 2 for SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models
Figure 3 for SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models
Figure 4 for SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models
Viaarxiv icon

StyleAdapter: A Single-Pass LoRA-Free Model for Stylized Image Generation

Add code
Sep 04, 2023
Viaarxiv icon

DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models

Add code
Jul 05, 2023
Figure 1 for DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models
Figure 2 for DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models
Figure 3 for DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models
Figure 4 for DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models
Viaarxiv icon

T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models

Add code
Feb 16, 2023
Viaarxiv icon

Mitigating Artifacts in Real-World Video Super-Resolution Models

Add code
Dec 14, 2022
Viaarxiv icon

Rethinking Alignment in Video Super-Resolution Transformers

Add code
Jul 18, 2022
Figure 1 for Rethinking Alignment in Video Super-Resolution Transformers
Figure 2 for Rethinking Alignment in Video Super-Resolution Transformers
Figure 3 for Rethinking Alignment in Video Super-Resolution Transformers
Figure 4 for Rethinking Alignment in Video Super-Resolution Transformers
Viaarxiv icon

VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

Add code
May 13, 2022
Figure 1 for VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
Figure 2 for VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
Figure 3 for VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
Figure 4 for VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
Viaarxiv icon

NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results

Add code
Apr 25, 2022
Figure 1 for NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
Figure 2 for NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
Figure 3 for NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
Figure 4 for NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
Viaarxiv icon

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

Add code
Aug 17, 2021
Figure 1 for Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
Figure 2 for Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
Figure 3 for Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
Figure 4 for Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
Viaarxiv icon