v0.5.2

What's Changed

• 🔥🔥[∆-DiT] ∆-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers by @DefTruth in #21
• 🔥🔥[DuCa] Accelerating Diffusion Transformers with Dual Feature Caching by @DefTruth in #22
• 🔥🔥[FBCache] Fastest HunyuanVideo Inference with Context Parallelism and First Block Cache on NVIDIA L20 GPUs by @DefTruth in #23
• 🔥🔥[SVDQuant] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models by @songh11 in #24
• 🔥[AB-Cache] AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse by @DefTruth in #25

New Contributors

• @songh11 made their first contribution in #24

Full Changelog: v0.5.1...v0.5.2

v0.5.1 Cache DiT

What's Changed

• 🔥[LinFusion] LINFUSION: 1 GPU, 1 MINUTE, 16K IMAGE by @DefTruth in #10
• 🔥[DC-Solver] DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation by @DefTruth in #11
• 🔥🔥[AdaCache] Adaptive Caching for Faster Video Generation with Diffusion Transformers by @DefTruth in #12
• 🔥🔥[TokenCache] Token Caching for Diffusion Transformer Acceleration by @DefTruth in #13
• 🔥🔥[TeaCache] Timestep Embedding Tells: It’s Time to Cache for Video Diffusion Model by @DefTruth in #14
• 🔥🔥[LazyDiT] LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers by @DefTruth in #15
• 🔥🔥[Ca2-VDM] Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing by @DefTruth in #16
• 🔥🔥[SmoothCache] SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers by @DefTruth in #17
• 🔥🔥[FasterCache] FASTERCACHE: TRAINING-FREE VIDEO DIFFUSION MODEL ACCELERATION WITH HIGH QUALITY by @DefTruth in #18
• 🔥🔥[ToCa] ToCa: Accelerating Diffusion Transformers with Token-wise Feature Caching by @DefTruth in #19
• 🔥🔥[SkipCache] Accelerating Vision Diffusion Transformers with Skip Branches by @DefTruth in #20

Full Changelog: v0.5...v0.5.1

v0.5

What's Changed

• 🔥[VQ4DiT] VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers by @DefTruth in #3
• 🔥[LBQ] Low-Bitwidth Floating Point Quantization for Efficient High-Quality Diffusion Models by @DefTruth in #4
• 🔥[EE-Diffusion] A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models by @DefTruth in #5
• 🔥[TFM-PTQ] Temporal Feature Matters: A Framework for Diffusion Model Quantization by @DefTruth in #6
• 🔥[Diffusion-RWKV] Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models by @DefTruth in #7
• Add 📙Awesome SD Inference with Sampling by @DefTruth in #8
• Bump up to v0.5 by @DefTruth in #9

Full Changelog: v0.3...v0.5

v0.3

What's Changed

• 🔥[DiTFastAttn] DiTFastAttn: Attention Compression for Diffusion Trans… by @DefTruth in #1
• Add [Other Awesome SD Inference Paper with codes] by @DefTruth in #2

New Contributors

• @DefTruth made their first contribution in #1

Full Changelog: v0.2...v0.3

v0.2: Fast-Forward Caching

Full Changelog: v0.1...v0.2

v0.1

Full Changelog: https://github.com/DefTruth/Awesome-SD-Distributed-Inference/commits/v0.1