We offer a free tool to upscale images with AI. Our image enhanser is free and easy to use on this website. Check the free image enhancer here.

If you want to use our tool upscale your images professionally we offer 2 ways to do so, as a SAAS solution as well as a standalone solution. The standalone solution comes plug and play on on a dedicated notebook. Both solutions will be updated with regular intervals.

Contact us for more details about these products via info@istanto.net

Blind face restoration (model 1)usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality references are inaccessible, limiting the applicability in real-world scenarios. 

The second model mainly contains two parts: (a) the off-line generation of multi-scale component dictionaries from large amounts of high-quality images, which have diverse poses and expressions. K-means is adopted to generate K clusters for each component (i.e., left/right eyes, nose and mouth) on different feature scales. (b) The restoration process and dictionary feature transfer (DFT) block that are utilized to provide the reference details in a progressive manner. Here, DFT-i block takes the Scale-i component dictionaries for reference in the same feature level.

Model 3 demo will be released soon. This model is not based on a GAN but is a so called "diffusion model". Over the past 20 years, the use of variational methods and nonlinear partial differential equations (PDEs) has significantly grown and evolved to address the image restoration problem. Here we consider image restoration as the classical inverse problem in which a piecewise smooth image is recovered from noisy data. The challenging aspect of this problem is to design methods which can selectively filter extraneous information, such as noise, without losing significant features or creating false ones. Many nonlinear models have been proposed for this purpose, however, when an image consists of objects of nonuniform intensity or has been degraded by noise, some of the most successful noise removal techniques which retain and even enhance sharp edges often exhibit a ’stair casing effect’. This can result in the generation of false edges which may in turn yield an incorrect segmentation. Our goal is to study a new model for image restoration which not only removes noise and retains sharp edges, but also avoids stair casing in what should be smooth regions.

Have a look at a test we ran on the SCFace dataset model 1 and model 2