Consistency Models

Authors: Yang Song, Prafulla Dhariwal, Mark Chen, Ilya Sutskever

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Through extensive experiments, we demonstrate that they outperform existing distillation techniques for diffusion models in one- and few-step sampling, achieving the new state-of-the-art FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 for one-step generation. When trained in isolation, consistency models become a new family of generative models that can outperform existing one-step, non-adversarial generative models on standard benchmarks such as CIFAR-10, ImageNet 64x64 and LSUN 256x256.
Researcher Affiliation Industry 1Open AI, San Francisco, CA 94110, USA. Correspondence to: Yang Song <songyang@openai.com>.
Pseudocode Yes Algorithm 1 Multistep Consistency Sampling, Algorithm 2 Consistency Distillation (CD), Algorithm 3 Consistency Training (CT).
Open Source Code No The paper does not include an unambiguous statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes We employ consistency distillation and consistency training to learn consistency models on real image datasets, including CIFAR-10 (Krizhevsky et al., 2009), ImageNet 64x64 (Deng et al., 2009), LSUN Bedroom 256x256, and LSUN Cat 256x256 (Yu et al., 2015).
Dataset Splits No The paper references standard datasets like CIFAR-10, ImageNet, and LSUN, which have predefined splits, but does not explicitly state the training, validation, or test dataset splits (e.g., percentages or sample counts) within the paper itself.
Hardware Specification Yes We trained all models on a cluster of Nvidia A100 GPUs.
Software Dependencies No The paper mentions 'Rectified Adam optimizer' but does not provide specific version numbers for software components like programming languages (e.g., Python), deep learning frameworks (e.g., PyTorch, TensorFlow), or CUDA libraries.
Experiment Setup Yes Table 3: Hyperparameters used for training CD and CT models, which includes Learning rate, Batch size, ODE solver, EMA decay rate, Training iterations, Mixed-Precision (FP16), Dropout probability, and Number of GPUs.