High-Resolution Image Editing via Multi-Stage Blended Diffusion
- URL: http://arxiv.org/abs/2210.12965v1
- Date: Mon, 24 Oct 2022 06:07:35 GMT
- Title: High-Resolution Image Editing via Multi-Stage Blended Diffusion
- Authors: Johannes Ackermann, Minjun Li
- Abstract summary: We propose an approach that uses a pre-trained low-resolution diffusion model to edit images in the megapixel range.
We first use Blended Diffusion to edit the image at a low resolution, and then upscale it in multiple stages, using a super-resolution model and Blended Diffusion.
- Score: 3.834509400202395
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Diffusion models have shown great results in image generation and in image
editing. However, current approaches are limited to low resolutions due to the
computational cost of training diffusion models for high-resolution generation.
We propose an approach that uses a pre-trained low-resolution diffusion model
to edit images in the megapixel range. We first use Blended Diffusion to edit
the image at a low resolution, and then upscale it in multiple stages, using a
super-resolution model and Blended Diffusion. Using our approach, we achieve
higher visual fidelity than by only applying off the shelf super-resolution
methods to the output of the diffusion model. We also obtain better global
consistency than directly using the diffusion model at a higher resolution.
Related papers
- DeltaDiff: A Residual-Guided Diffusion Model for Enhanced Image Super-Resolution [9.948203187433196]
We propose a new diffusion model called Deltadiff, which uses only residuals between images for diffusion.
Our method surpasses state-of-the-art models and generates results with better fidelity.
arXiv Detail & Related papers (2025-02-18T06:07:14Z) - One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation [60.54811860967658]
FluxSR is a novel one-step diffusion Real-ISR based on flow matching models.
First, we introduce Flow Trajectory Distillation (FTD) to distill a multi-step flow matching model into a one-step Real-ISR.
Second, to improve image realism and address high-frequency artifact issues in generated images, we propose TV-LPIPS as a perceptual loss.
arXiv Detail & Related papers (2025-02-04T04:11:29Z) - Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution [35.55094110634178]
We propose an efficient conditional diffusion model with probability flow sampling for image super-resolution.
Our method achieves higher super-resolution quality than existing diffusion-based image super-resolution methods.
arXiv Detail & Related papers (2024-04-16T16:08:59Z) - Make a Cheap Scaling: A Self-Cascade Diffusion Model for
Higher-Resolution Adaptation [112.08287900261898]
This paper proposes a novel self-cascade diffusion model for rapid adaptation to higher-resolution image and video generation.
Our approach achieves a 5X training speed-up and requires only an additional 0.002M tuning parameters.
Experiments demonstrate that our approach can quickly adapt to higher resolution image and video synthesis by fine-tuning for just 10k steps, with virtually no additional inference time.
arXiv Detail & Related papers (2024-02-16T07:48:35Z) - HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models [13.68666823175341]
HiDiffusion is a tuning-free higher-resolution framework for image synthesis.
RAU-Net dynamically adjusts the feature map size to resolve object duplication.
MSW-MSA engages optimized window attention to reduce computations.
arXiv Detail & Related papers (2023-11-29T11:01:38Z) - ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with
Diffusion Models [126.35334860896373]
We investigate the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes.
Existing works for higher-resolution generation, such as attention-based and joint-diffusion approaches, cannot well address these issues.
We propose a simple yet effective re-dilation that can dynamically adjust the convolutional perception field during inference.
arXiv Detail & Related papers (2023-10-11T17:52:39Z) - Prompt-tuning latent diffusion models for inverse problems [72.13952857287794]
We propose a new method for solving imaging inverse problems using text-to-image latent diffusion models as general priors.
Our method, called P2L, outperforms both image- and latent-diffusion model-based inverse problem solvers on a variety of tasks, such as super-resolution, deblurring, and inpainting.
arXiv Detail & Related papers (2023-10-02T11:31:48Z) - ACDMSR: Accelerated Conditional Diffusion Models for Single Image
Super-Resolution [84.73658185158222]
We propose a diffusion model-based super-resolution method called ACDMSR.
Our method adapts the standard diffusion model to perform super-resolution through a deterministic iterative denoising process.
Our approach generates more visually realistic counterparts for low-resolution images, emphasizing its effectiveness in practical scenarios.
arXiv Detail & Related papers (2023-07-03T06:49:04Z) - Simple diffusion: End-to-end diffusion for high resolution images [27.47227724865238]
This paper aims to improve denoising diffusion for high resolution images while keeping the model as simple as possible.
The four main findings are: 1) the noise schedule should be adjusted for high resolution images, 2) It is sufficient to scale only a particular part of the architecture, 3) dropout should be added at specific locations in the architecture, and 4) downsampling is an effective strategy to avoid high resolution feature maps.
arXiv Detail & Related papers (2023-01-26T13:35:02Z) - Cascaded Diffusion Models for High Fidelity Image Generation [53.57766722279425]
We show that cascaded diffusion models are capable of generating high fidelity images on the class-conditional ImageNet generation challenge.
A cascaded diffusion model comprises a pipeline of multiple diffusion models that generate images of increasing resolution.
We find that the sample quality of a cascading pipeline relies crucially on conditioning augmentation.
arXiv Detail & Related papers (2021-05-30T17:14:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.