Logan Roundski PRO

CCP6's activity

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

upvoted a paper 1 day ago

RealisVSR: Detail-enhanced Diffusion for Real-World 4K Video Super-Resolution

Paper • 2507.19138 • Published 4 days ago • 1

upvoted a paper 3 days ago

nablaNABLA: Neighborhood Adaptive Block-Level Attention

Paper • 2507.13546 • Published 11 days ago • 110

upvoted a paper 4 days ago

PUSA V1.0: Surpassing Wan-I2V with $500 Training Cost by Vectorized Timestep Adaptation

Paper • 2507.16116 • Published 7 days ago • 9

upvoted a paper 5 days ago

Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers

Paper • 2507.08422 • Published 18 days ago • 34

upvoted a collection 6 days ago

AI Math: Diffusion

Collection

144 items • Updated 25 days ago • 1

upvoted a paper 20 days ago

High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning

Paper • 2507.05920 • Published 21 days ago • 11

upvoted a paper 22 days ago

MAKIMA: Tuning-free Multi-Attribute Open-domain Video Editing via Mask-Guided Attention Modulation

Paper • 2412.19978 • Published Dec 28, 2024 • 1

upvoted 2 papers about 1 month ago

UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions

Paper • 2506.13691 • Published Jun 16 • 2

Normalized Attention Guidance: Universal Negative Guidance for Diffusion Model

Paper • 2505.21179 • Published May 27 • 13

upvoted a collection about 2 months ago

SeedVR

Collection

A diffusion transformer model for high-resolution image and video restoration. • 9 items • Updated 12 days ago • 7

upvoted 2 papers about 2 months ago

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

Paper • 2506.05301 • Published Jun 5 • 55

ATI: Any Trajectory Instruction for Controllable Video Generation

Paper • 2505.22944 • Published May 28 • 7

upvoted a collection 2 months ago

Wan2.1 14B T2V LoRAs

Collection

A collection of Remade's Wan2.1 14B T2V LoRAs • 20 items • Updated Mar 27 • 31

upvoted a paper 3 months ago

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

Paper • 2505.04512 • Published May 7 • 36

upvoted a collection 5 months ago

video-effects

Collection

Fine-tunes of open video generation models like CogVideoX to emulate cool video effects like "squish", "dissolve", "cakeify", etc. Pika inspired. • 8 items • Updated Mar 8 • 7

upvoted 2 papers over 1 year ago

Evolutionary Optimization of Model Merging Recipes

Paper • 2403.13187 • Published Mar 19, 2024 • 56

HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models

Paper • 2312.00079 • Published Nov 30, 2023 • 17