xziayro

xziayro's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 21 days ago

FreSca: Unveiling the Scaling Space in Diffusion Models

Paper • 2504.02154 • Published 25 days ago • 18

upvoted 2 papers 26 days ago

TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes

Paper • 2503.23461 • Published 29 days ago • 94

GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

Paper • 2504.01016 • Published 27 days ago • 29

upvoted a paper 28 days ago

Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

Paper • 2503.22236 • Published about 1 month ago • 11

upvoted 16 papers about 1 month ago

Synthetic Video Enhances Physical Fidelity in Video Synthesis

Paper • 2503.20822 • Published Mar 26 • 16

Optimal Stepsize for Diffusion Sampling

Paper • 2503.21774 • Published Mar 27 • 13

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

Paper • 2503.21758 • Published Mar 27 • 21

LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis

Paper • 2503.21749 • Published Mar 27 • 26

MagicComp: Training-free Dual-Phase Refinement for Compositional Video Generation

Paper • 2503.14428 • Published Mar 18 • 8

Training-free Diffusion Acceleration with Bottleneck Sampling

Paper • 2503.18940 • Published Mar 24 • 12

When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO

Paper • 2503.16921 • Published Mar 21 • 6

Enabling Versatile Controls for Video Diffusion Models

Paper • 2503.16983 • Published Mar 21 • 15

BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing

Paper • 2503.13434 • Published Mar 17 • 26

Personalize Anything for Free with Diffusion Transformer

Paper • 2503.12590 • Published Mar 16 • 44

Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection

Paper • 2503.12271 • Published Mar 15 • 9

FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis

Paper • 2503.13265 • Published Mar 17 • 15

Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation

Paper • 2503.13424 • Published Mar 17 • 30

Efficient Personalization of Quantized Diffusion Model without Backpropagation

Paper • 2503.14868 • Published Mar 19 • 20

Temporal Regularization Makes Your Video Generator Stronger

Paper • 2503.15417 • Published Mar 19 • 22

XAttention: Block Sparse Attention with Antidiagonal Scoring

Paper • 2503.16428 • Published Mar 20 • 14