Picture for Ming-Yu Liu

Ming-Yu Liu

Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models

Add code
Nov 11, 2024
Viaarxiv icon

Edify 3D: Scalable High-Quality 3D Asset Generation

Add code
Nov 11, 2024
Figure 1 for Edify 3D: Scalable High-Quality 3D Asset Generation
Figure 2 for Edify 3D: Scalable High-Quality 3D Asset Generation
Figure 3 for Edify 3D: Scalable High-Quality 3D Asset Generation
Figure 4 for Edify 3D: Scalable High-Quality 3D Asset Generation
Viaarxiv icon

One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation

Add code
Oct 28, 2024
Figure 1 for One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation
Figure 2 for One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation
Figure 3 for One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation
Figure 4 for One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation
Viaarxiv icon

EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation

Add code
Sep 26, 2024
Figure 1 for EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
Figure 2 for EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
Figure 3 for EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
Figure 4 for EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
Viaarxiv icon

Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling

Add code
Sep 04, 2024
Figure 1 for Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
Figure 2 for Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
Figure 3 for Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
Figure 4 for Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
Viaarxiv icon

Wolf: Captioning Everything with a World Summarization Framework

Add code
Jul 26, 2024
Figure 1 for Wolf: Captioning Everything with a World Summarization Framework
Figure 2 for Wolf: Captioning Everything with a World Summarization Framework
Figure 3 for Wolf: Captioning Everything with a World Summarization Framework
Figure 4 for Wolf: Captioning Everything with a World Summarization Framework
Viaarxiv icon

JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation

Add code
Jul 08, 2024
Figure 1 for JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation
Figure 2 for JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation
Figure 3 for JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation
Figure 4 for JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation
Viaarxiv icon

Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation

Add code
Apr 30, 2024
Viaarxiv icon

Condition-Aware Neural Network for Controlled Image Generation

Add code
Apr 01, 2024
Figure 1 for Condition-Aware Neural Network for Controlled Image Generation
Figure 2 for Condition-Aware Neural Network for Controlled Image Generation
Figure 3 for Condition-Aware Neural Network for Controlled Image Generation
Figure 4 for Condition-Aware Neural Network for Controlled Image Generation
Viaarxiv icon

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

Add code
Mar 07, 2024
Figure 1 for DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Figure 2 for DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Figure 3 for DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Figure 4 for DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Viaarxiv icon