AI model preview image
Diffusion Autoencoders (DiffAE) is a model that is used for image manipulation. It leverages the power of autoencoder architectures and combines it with a diffusion process to generate high-quality and realistic image modifications. The model is trained to learn the underlying structure of a dataset of images and is then able to perform various image manipulations such as object removal, colorization, style transfer, and more. The diffusion process allows for controlled and smooth transitions between the original and modified images, resulting in visually pleasing and natural-looking modifications.

Use cases

Diffusion Autoencoders (DiffAE) have a wide range of use cases in image manipulation. For photographers and designers, this model can be used to easily remove unwanted objects or alter the colors of an image. It can also be used for artistic purposes, such as creating stylized versions of images or generating new images with specific visual characteristics. In the field of computer graphics, DiffAE can be used to generate realistic textures or modify the appearance of 3D models. Additionally, this model could find applications in the fashion industry, allowing users to experiment with different styles and colors of clothing on a virtual model. Overall, DiffAE has the potential to be integrated into various software tools and platforms, enabling users to easily perform complex image manipulations in a controlled and visually appealing manner. Potential products or practical uses of this model could include a photo editing software with advanced image manipulation features, a virtual try-on application for clothing retailers, or an augmented reality tool for creating realistic and interactive virtual environments.



Cost per run
Avg run time
Nvidia T4 GPU

Creator Models

Pix2pix Zero$?4,206
Night Enhancement$0.0104520,721
Mindall E$?1,645
Compositional Vsual Generation With Composable Diffusion Models Pytorch$0.01155774

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Diffae model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameDiffae
Image Manipulatinon with Diffusion Autoencoders
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkView on Arxiv


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$0.02365
Prediction HardwareNvidia T4 GPU
Average Completion Time43 seconds