17 33 2

Oğuzhan Ercan

oguzhanercan

AI & ML interests

Computer Vision, Generative Vision, first trajectory bender

Recent Activity

updated a dataset 1 day ago

oguzhanercan/Text2Face

updated a collection 1 day ago

Diffusion Model Control

upvoted a paper 1 day ago

Nested Attention: Semantic-aware Attention Values for Concept Personalization

View all activity

Organizations

None yet

oguzhanercan's activity

upvoted a paper 1 day ago

Nested Attention: Semantic-aware Attention Values for Concept Personalization

Paper • 2501.01407 • Published 3 days ago • 9

upvoted 2 papers 3 days ago

VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control

Paper • 2501.01427 • Published 3 days ago • 40

Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

Paper • 2501.01423 • Published 3 days ago • 31

upvoted a paper 4 days ago

1.58-bit FLUX

Paper • 2412.18653 • Published 12 days ago • 66

upvoted a paper 12 days ago

DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation

Paper • 2412.18597 • Published 12 days ago • 19

upvoted a paper 14 days ago

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up

Paper • 2412.16112 • Published 17 days ago • 21

upvoted a paper 20 days ago

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens

Paper • 2412.10208 • Published 24 days ago • 19

upvoted a paper 21 days ago

FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers

Paper • 2412.09611 • Published 24 days ago • 9

upvoted 2 papers 24 days ago

Generative World Explorer

Paper • 2411.11844 • Published Nov 18, 2024 • 75

Learning Flow Fields in Attention for Controllable Person Image Generation

Paper • 2412.08486 • Published 26 days ago • 32

upvoted a paper 25 days ago

StyleMaster: Stylize Your Video with Artistic Generation and Translation

Paper • 2412.07744 • Published 27 days ago • 19

upvoted 4 papers 26 days ago

OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision

Paper • 2411.07199 • Published Nov 11, 2024 • 46

EMOv2: Pushing 5M Vision Model Frontier

Paper • 2412.06674 • Published 28 days ago • 13

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

Paper • 2412.07589 • Published 27 days ago • 46

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

Paper • 2412.07774 • Published 26 days ago • 25

upvoted 3 papers about 1 month ago

Negative Token Merging: Image-based Adversarial Feature Guidance

Paper • 2412.01339 • Published Dec 2, 2024 • 22

NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training

Paper • 2412.02030 • Published Dec 2, 2024 • 18

WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model

Paper • 2411.17459 • Published Nov 26, 2024 • 10

upvoted 2 papers 2 months ago

CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes

Paper • 2411.00771 • Published Nov 1, 2024 • 9

MarDini: Masked Autoregressive Diffusion for Video Generation at Scale

Paper • 2410.20280 • Published Oct 26, 2024 • 23