Picture for Wendi Zheng

Wendi Zheng

Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer

Add code
May 08, 2024
Figure 1 for Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer
Figure 2 for Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer
Figure 3 for Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer
Figure 4 for Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer
Viaarxiv icon

CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion

Add code
Mar 08, 2024
Figure 1 for CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion
Figure 2 for CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion
Figure 3 for CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion
Figure 4 for CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion
Viaarxiv icon

Multi-Agent Collaboration Framework for Recommender Systems

Add code
Feb 23, 2024
Viaarxiv icon

Relay Diffusion: Unifying diffusion process across resolutions for image synthesis

Add code
Sep 04, 2023
Figure 1 for Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
Figure 2 for Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
Figure 3 for Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
Figure 4 for Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
Viaarxiv icon

GLM-130B: An Open Bilingual Pre-trained Model

Add code
Oct 05, 2022
Figure 1 for GLM-130B: An Open Bilingual Pre-trained Model
Figure 2 for GLM-130B: An Open Bilingual Pre-trained Model
Figure 3 for GLM-130B: An Open Bilingual Pre-trained Model
Figure 4 for GLM-130B: An Open Bilingual Pre-trained Model
Viaarxiv icon

CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

Add code
May 29, 2022
Figure 1 for CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
Figure 2 for CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
Figure 3 for CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
Figure 4 for CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
Viaarxiv icon

CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers

Add code
Apr 28, 2022
Figure 1 for CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
Figure 2 for CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
Figure 3 for CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
Figure 4 for CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
Viaarxiv icon

CogView: Mastering Text-to-Image Generation via Transformers

Add code
May 28, 2021
Figure 1 for CogView: Mastering Text-to-Image Generation via Transformers
Figure 2 for CogView: Mastering Text-to-Image Generation via Transformers
Figure 3 for CogView: Mastering Text-to-Image Generation via Transformers
Figure 4 for CogView: Mastering Text-to-Image Generation via Transformers
Viaarxiv icon