Accelerating auto-regressive text-to-image generation with training-free speculative jacobi decoding

Y Teng, H Shi, X Liu, X Ning, G Dai, Y Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
The current large auto-regressive models can generate high-quality, high-resolution images,
but these models require hundreds or even thousands of steps of next-token prediction …

Rectified diffusion: Straightness is not your need in rectified flow

FY Wang, L Yang, Z Huang, M Wang, H Li - arxiv preprint arxiv …, 2024 - arxiv.org
Diffusion models have greatly improved visual generation but are hindered by slow
generation speed due to the computationally intensive nature of solving generative ODEs …

Osv: One step is enough for high-quality image to video generation

X Mao, Z Jiang, FY Wang, W Zhu, J Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
Video diffusion models have shown great potential in generating high-quality videos,
making them an increasingly popular focus. However, their inherent iterative nature leads to …

Stable Consistency Tuning: Understanding and Improving Consistency Models

FY Wang, Z Geng, H Li - arxiv preprint arxiv:2410.18958, 2024 - arxiv.org
Diffusion models achieve superior generation quality but suffer from slow generation speed
due to the iterative nature of denoising. In contrast, consistency models, a new generative …

-VAE: Denoising as Visual Decoding

L Zhao, S Woo, Z Wan, Y Li, H Zhang, B Gong… - arxiv preprint arxiv …, 2024 - arxiv.org
In generative modeling, tokenization simplifies complex data into compact, structured
representations, creating a more efficient, learnable space. For high-dimensional visual …

Animatelcm: Computation-efficient personalized style video generation without personalized video data

FY Wang, Z Huang, W Bian, X Shi, K Sun… - SIGGRAPH Asia 2024 …, 2024 - dl.acm.org
This paper introduces an effective method for computation-efficient personalized style video
generation without requiring access to any personalized video data. It reduces the …

Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled Guidance

C Wang, Z Guo, Y Duan, H Li, N Chen, X Tang… - arxiv preprint arxiv …, 2024 - arxiv.org
Consistency distillation methods have demonstrated significant success in accelerating
generative tasks of diffusion models. However, since previous consistency distillation …

Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples

N Vouitsis, R Hosseinzadeh, BL Ross… - arxiv preprint arxiv …, 2024 - arxiv.org
Although diffusion models can generate remarkably high-quality samples, they are
intrinsically bottlenecked by their expensive iterative sampling procedure. Consistency …

Real-time One-Step Diffusion-based Expressive Portrait Videos Generation

H Guo, H Yi, D Zhou, AW Bergman… - arxiv preprint arxiv …, 2024 - arxiv.org
Latent diffusion models have made great strides in generating expressive portrait videos
with accurate lip-sync and natural motion from a single reference image and audio input …

MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model

L Jiang, Y Wei, H Ni - arxiv preprint arxiv:2501.19083, 2025 - arxiv.org
Diffusion models have become a popular choice for human motion synthesis due to their
powerful generative capabilities. However, their high computational complexity and large …