Oğuzhan Ercan

oguzhanercan

AI & ML interests

Computer Vision, Generative Vision, first trajectory bender

Recent Activity

upvoted a paper about 22 hours ago

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

updated a collection about 23 hours ago

Video Generation

liked a model 3 days ago

kudzueye/boreal-flux-dev-v2

View all activity

Organizations

None yet

oguzhanercan's activity

commented a paper 6 days ago

Steering Rectified Flow Models in the Vector Field for Controlled Image Generation

Paper • 2412.00100 • Published 28 days ago • 16 •

commented a paper 14 days ago

Learning Flow Fields in Attention for Controllable Person Image Generation

Paper • 2412.08486 • Published 15 days ago • 32 •

commented 2 papers 15 days ago

SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion

Paper • 2412.04301 • Published 21 days ago • 32 •

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

Paper • 2412.07774 • Published 15 days ago • 25 •

commented 2 papers 20 days ago

Negative Token Merging: Image-based Adversarial Feature Guidance

Paper • 2412.01339 • Published 24 days ago • 21 •

Negative Token Merging: Image-based Adversarial Feature Guidance

Paper • 2412.01339 • Published 24 days ago • 21 •

New activity in ChenDY/NitroFusion 20 days ago

ControlNets

#1 opened 20 days ago by

oguzhanercan

commented a paper 21 days ago

Steering Rectified Flow Models in the Vector Field for Controlled Image Generation

Paper • 2412.00100 • Published 28 days ago • 16 •

commented 2 papers 23 days ago

Steering Rectified Flow Models in the Vector Field for Controlled Image Generation

Paper • 2412.00100 • Published 28 days ago • 16 •

Steering Rectified Flow Models in the Vector Field for Controlled Image Generation

Paper • 2412.00100 • Published 28 days ago • 16 •

commented a paper 28 days ago

Physics in Next-token Prediction

Paper • 2411.00660 • Published Nov 1 • 14 •

New activity in HighCWu/FLUX.1-dev-4bit about 1 month ago

Questions about LoRA

#5 opened 3 months ago by

tungdop2

commented 2 papers about 2 months ago

Face Anonymization Made Simple

Paper • 2411.00762 • Published Nov 1 • 7 •

Face Anonymization Made Simple

Paper • 2411.00762 • Published Nov 1 • 7 •

New activity in PrunaAI/FLUX.1-schnell-4bit about 2 months ago

Can't get attribute'EmbedND'

#3 opened about 2 months ago by

oguzhanercan

New activity in sayakpaul/flux.1-dev-nf4-with-bnb-integration 2 months ago

Bitsandbytes installation problem

#4 opened 2 months ago by

oguzhanercan

commented 3 papers 2 months ago

MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models

Paper • 2410.13370 • Published Oct 17 • 35 •

MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models

Paper • 2410.13370 • Published Oct 17 • 35 •

Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models

Paper • 2410.11081 • Published Oct 14 • 19 •

commented a paper 3 months ago

Addition is All You Need for Energy-efficient Language Models

Paper • 2410.00907 • Published Oct 1 • 144 •