wenhao

costwen's activity

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

upvoted 2 papers 9 days ago

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

Paper • 2510.12586 • Published 12 days ago • 106

ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints

Paper • 2510.14847 • Published 10 days ago • 53

upvoted a paper 2 months ago

S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

Paper • 2508.12880 • Published Aug 18 • 46

upvoted a paper 3 months ago

Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

Paper • 2508.07981 • Published Aug 11 • 58

upvoted a paper 4 months ago

AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models

Paper • 2506.19851 • Published Jun 24 • 60

updated a dataset about 1 year ago

costwen/objvarse_simply

Viewer • Updated Sep 30, 2024 • 192k • 3

updated a model about 1 year ago

costwen/Ouroboros3D

Updated Aug 30, 2024

authored 2 papers about 1 year ago

Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion

Paper • 2406.03184 • Published Jun 5, 2024 • 22

EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

Paper • 2312.06725 • Published Dec 11, 2023 • 1

liked a model almost 2 years ago

playgroundai/playground-v2-256px-base

Text-to-Image • Updated Feb 22, 2024 • 22 • 20

updated a collection almost 2 years ago

3d

Collection

3 items • Updated Nov 26, 2023

liked a Space over 2 years ago

Running on CPU Upgrade

11.4k

11.4k

Stable Diffusion 2-1

🔥

Generate images from text prompts