FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis
In this study, we delve into the generation of high-resolution images from pre-trained diffusion models, addressing persistent challenges, such as repetitive patterns and structural distortions, that emerge when models are applied beyond their trained resolutions. To address this issue, we introduce an innovative, training-free approach FouriScale from the perspective of frequency domain analysis. We replace the original convolutional layers in pre-trained diffusion models by incorporating a dilation technique along with a low-pass operation, intending to achieve structural consistency and scale consistency across resolutions, respectively. Further enhanced by a padding-then-crop strategy, our method can flexibly handle text-to-image generation of various aspect ratios. By using the FouriScale as guidance, our method successfully balances the structural integrity and fidelity of generated images, achieving an astonishing capacity of arbitrary-size, high-resolution, and high-quality generation. With its simplicity and compatibility, our method can provide valuable insights for future explorations into the synthesis of ultra-high-resolution images. The code will be released at https://github.com/LeonHLJ/FouriScale.
Code (1)
Tasks
Image GenerationText to Image GenerationText-to-Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Rethinking the Defense Against Free-rider Attack From the Perspective of Model Weight Evolving Frequency
Federated learning (FL) is a distributed machine learning approach where multiple clients collaboratively train a joint model without exchanging their data. Despite FL's unprecedented success in data privacy-preserving, …
Federated LearningPrivacy PreservingIdentity-Preserving Text-to-Video Generation by Frequency Decomposition
Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an open problem for generative models. This…
Human-Domain Subject-to-VideoImage to Video GenerationOpen-Domain Subject-to-VideoText-to-Video Generation+1FreqForcing: Autoregressive Long Video Generation via Spectral Self-Anchoring
Autoregressive video diffusion models enable real-time streaming video generation. However, errors introduced during self-rollout accumulate over long horizons, manifesting as color drift, motion stagnation, and eventual…
Video GenerationRethinking Oversaturation in Classifier-Free Guidance via Low Frequency
Classifier-free guidance (CFG) succeeds in condition diffusion models that use a guidance scale to balance the influence of conditional and unconditional terms. A high guidance scale is used to enhance the performance of…
When Training-Free NAS Meets Vision Transformer: A Neural Tangent Kernel Perspective
This paper investigates the Neural Tangent Kernel (NTK) to search vision transformers without training. In contrast with the previous observation that NTK-based metrics can effectively predict CNNs performance at initial…
image-classificationImage ClassificationSemantic Segmentation