Tolga Cangöz

tolgacangoz's activity

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

upvoted a paper 1 day ago

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation

Paper • 2607.21553 • Published 3 days ago • 21

upvoted an article 3 days ago

view article

Article

Bringing Nunchaku 4-bit Diffusion Inference to Diffusers

• 
• 

rootonchair, sayakpaul

•

3 days ago

• 43

upvoted an article 8 days ago

view article

Article

Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers

• 

nvidia

•

8 days ago

• 79

upvoted an article 10 days ago

view article

Article

Security incident disclosure — July 2026

• 

system

•

10 days ago

• 651

upvoted 3 papers 10 days ago

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

Paper • 2602.02493 • Published Feb 2 • 47

Alchemist: Turning Public Text-to-Image Data into Generative Gold

Paper • 2505.19297 • Published May 25, 2025 • 86

TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training

Paper • 2501.04765 • Published Jan 8, 2025 • 1

upvoted a paper 11 days ago

Contrastive Flow Matching

Paper • 2506.05350 • Published Jun 5, 2025 • 1

upvoted an article 12 days ago

view article

Article

Sensitivity Aware Mixed Precision Quantization V1

• 

badaoui

•

Jun 13, 2025

• 28

upvoted 2 papers 14 days ago

REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

Paper • 2505.16792 • Published May 22, 2025 • 1

What matters for Representation Alignment: Global Information or Spatial Structure?

Paper • 2512.10794 • Published Dec 11, 2025 • 11

upvoted a paper 16 days ago

VOID: Video Object and Interaction Deletion

Paper • 2604.02296 • Published Apr 2 • 57

upvoted an article 16 days ago

view article

Article

Profiling in PyTorch (Part 3): Attention is all you profile

• 
• 
• +2

ariG23498, sergiopaniego, sayakpaul, ror

•

16 days ago

• 38

upvoted 2 papers 17 days ago

Is Noise Conditioning Necessary for Denoising Generative Models?

Paper • 2502.13129 • Published Feb 18, 2025 • 2

Back to Basics: Let Denoising Generative Models Denoise

Paper • 2511.13720 • Published Nov 17, 2025 • 71

upvoted 3 papers 18 days ago

Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

Paper • 2403.03206 • Published Mar 5, 2024 • 72

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Paper • 2310.00426 • Published Sep 30, 2023 • 63

DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space

Paper • 2508.00413 • Published Aug 1, 2025 • 7

upvoted 2 collections 18 days ago

LTX-2.3 Creative Lab

Collection

LoRAs and IC-LoRAs, trained on the LTX-2.3 model • 25 items • Updated 7 days ago • 83

PRX

Collection

PRX text-to-image models • 10 items • Updated Jun 12 • 17