Fast high-resolution image synthesis with latent adversarial diffusion distillation
Diffusion models are the main driver of progress in image and video synthesis, but suffer
from slow inference speed. Distillation methods, like the recently introduced adversarial …
from slow inference speed. Distillation methods, like the recently introduced adversarial …
Diffusion models and representation learning: A survey
Diffusion Models are popular generative modeling methods in various vision tasks, attracting
significant attention. They can be considered a unique instance of self-supervised learning …
significant attention. They can be considered a unique instance of self-supervised learning …
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 …
Videoagent: Self-improving video generation
Video generation has been used to generate visual plans for controlling robotic systems.
Given an image observation and a language instruction, previous work has generated video …
Given an image observation and a language instruction, previous work has generated video …
Flow generator matching
In the realm of Artificial Intelligence Generated Content (AIGC), flow-matching models have
emerged as a powerhouse, achieving success due to their robust theoretical underpinnings …
emerged as a powerhouse, achieving success due to their robust theoretical underpinnings …
From slow bidirectional to fast causal video generators
Current video diffusion models achieve impressive generation quality but struggle in
interactive applications due to bidirectional attention dependencies. The generation of a …
interactive applications due to bidirectional attention dependencies. The generation of a …
Adversarial diffusion compression for real-world image super-resolution
Real-world image super-resolution (Real-ISR) aims to reconstruct high-resolution images
from low-resolution inputs degraded by complex, unknown processes. While many Stable …
from low-resolution inputs degraded by complex, unknown processes. While many Stable …
Nitrofusion: High-fidelity single-step diffusion through dynamic adversarial training
DY Chen, H Bandyopadhyay, K Zou… - arxiv preprint arxiv …, 2024 - arxiv.org
We introduce NitroFusion, a fundamentally different approach to single-step diffusion that
achieves high-quality generation through a dynamic adversarial framework. While one-step …
achieves high-quality generation through a dynamic adversarial framework. While one-step …
Multistep Distillation of Diffusion Models via Moment Matching
We present a new method for making diffusion models faster to sample. The method distills
many-step diffusion models into few-step models by matching conditional expectations of …
many-step diffusion models into few-step models by matching conditional expectations of …
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 …