DiTFastAttn: Attention Compression for Diffusion Transformer Models Paper • 2406.08552 • Published Jun 12, 2024 • 26
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Paper • 2506.16054 • Published Jun 19 • 60
view post Post 8777 Self-Forcing - a real-time video distilled model from Wan 2.1 by @adobe is out, and they open sourced it 🐐I've built a live real time demo on Spaces 📹💨 multimodalart/self-forcing See translation 5 replies · ❤️ 11 11 🔥 6 6 + Reply
VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning Paper • 2504.07960 • Published Apr 10 • 50
LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis Paper • 2503.21749 • Published Mar 27 • 26
Lumina-Image 2.0: A Unified and Efficient Image Generative Framework Paper • 2503.21758 • Published Mar 27 • 22
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts Paper • 2503.02819 • Published Mar 4 • 2
Lumina-Video: Efficient and Flexible Video Generation with Multi-scale Next-DiT Paper • 2502.06782 • Published Feb 10 • 14
K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs Paper • 2502.18461 • Published Feb 25 • 16
Hyperstroke: A Novel High-quality Stroke Representation for Assistive Artistic Drawing Paper • 2408.09348 • Published Aug 18, 2024 • 1
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization Paper • 2405.17873 • Published May 28, 2024 • 3
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation Paper • 2406.02540 • Published Jun 4, 2024 • 3
E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling Paper • 2412.14170 • Published Dec 18, 2024
Preference Leakage: A Contamination Problem in LLM-as-a-judge Paper • 2502.01534 • Published Feb 3 • 41
PhenDiff: Revealing Invisible Phenotypes with Conditional Diffusion Models Paper • 2312.08290 • Published Dec 13, 2023 • 3
IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models Paper • 2501.13920 • Published Jan 23 • 19