Accelerating auto-regressive text-to-image generation with training-free speculative jacobi decoding
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 …
but these models require hundreds or even thousands of steps of next-token prediction …
Rectified diffusion: Straightness is not your need in rectified flow
Diffusion models have greatly improved visual generation but are hindered by slow
generation speed due to the computationally intensive nature of solving generative ODEs …
generation speed due to the computationally intensive nature of solving generative ODEs …
Osv: One step is enough for high-quality image to video generation
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 …
making them an increasingly popular focus. However, their inherent iterative nature leads to …
Stable Consistency Tuning: Understanding and Improving Consistency Models
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 …
due to the iterative nature of denoising. In contrast, consistency models, a new generative …
-VAE: Denoising as Visual Decoding
In generative modeling, tokenization simplifies complex data into compact, structured
representations, creating a more efficient, learnable space. For high-dimensional visual …
representations, creating a more efficient, learnable space. For high-dimensional visual …
Animatelcm: Computation-efficient personalized style video generation without personalized video data
This paper introduces an effective method for computation-efficient personalized style video
generation without requiring access to any personalized video data. It reduces the …
generation without requiring access to any personalized video data. It reduces the …
Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled Guidance
Consistency distillation methods have demonstrated significant success in accelerating
generative tasks of diffusion models. However, since previous consistency distillation …
generative tasks of diffusion models. However, since previous consistency distillation …
Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples
Although diffusion models can generate remarkably high-quality samples, they are
intrinsically bottlenecked by their expensive iterative sampling procedure. Consistency …
intrinsically bottlenecked by their expensive iterative sampling procedure. Consistency …
Real-time One-Step Diffusion-based Expressive Portrait Videos Generation
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 …
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 …
powerful generative capabilities. However, their high computational complexity and large …