SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers Paper • 2605.22668 • Published 24 days ago • 40
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation Paper • 2605.18739 • Published 27 days ago • 113
Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions Paper • 2604.23774 • Published Apr 29 • 17 • 4
Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions Paper • 2604.23774 • Published Apr 29 • 17
Video Analysis and Generation via a Semantic Progress Function Paper • 2604.22554 • Published Apr 24 • 63 • 4
Video Analysis and Generation via a Semantic Progress Function Paper • 2604.22554 • Published Apr 24 • 63
Video Analysis and Generation via a Semantic Progress Function Paper • 2604.22554 • Published Apr 24 • 63
ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control Paper • 2604.20816 • Published Apr 22 • 15
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning Paper • 2604.04746 • Published Apr 8 • 73
Running on Zero MCP Featured 2.23k Qwen Image Edit Camera Control 🎬 2.23k Fast 4 step inference with Qwen Image Edit 2509
LTX-2.3 Collection LTX-2.3 base models, quantized models and accompanying LoRAs and IC-LoRAs • 10 items • Updated 2 days ago • 58
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers Paper • 2603.28762 • Published Mar 30 • 25
AVControl: Efficient Framework for Training Audio-Visual Controls Paper • 2603.24793 • Published Mar 25 • 29