| --- |
| license: mit |
| --- |
| |
| # pOps: Photo-Inspired Diffusion Operators |
|
|
| <div align="center"> |
|
|
| [**Project Page**](https://popspaper.github.io/pOps/) **|** [**Paper**](https://popspaper.github.io/pOps/static/files/pOps_paper.pdf) **|** [**Code**](https://github.com/pOpsPaper/pOps) |
| </div> |
|
|
| --- |
|
|
|
|
| ## Introduction |
|
|
| <p align="center"> |
| <img src="https://popspaper.github.io/pOps/static/figures/teaser_pops.jpg" width="800px"/> |
| Different operators trained using pOps. Our method learns operators that are applied directly in the image embedding space, resulting in a variety of semantic operations that can then be realized as images using an image diffusion model. |
| </p> |
|
|
| ## Trained Operators |
| - [Texturing Operator](https://huggingface.co/pOpsPaper/operators/blob/main/models/texturing/learned_prior.pth): Given an image embedding of an object and an image embedding of a texture exemplar, paint the object with the provided texture. |
| - [Scene Operator](https://huggingface.co/pOpsPaper/operators/blob/main/models/scene/learned_prior.pth): Given an image embedding of an object and an image embedding representing a scene layout, generate an image placing the object within a semantically similar scene. |
| - [Union Operator](https://huggingface.co/pOpsPaper/operators/blob/main/models/union/learned_prior.pth): Given two image embeddings representing scenes with one or multiple objects, combine the objects appearing in the scenes into a single embedding composed of both objects. |
| - [Instruct Operator](https://huggingface.co/pOpsPaper/operators/blob/main/models/instruct/learned_prior.pth): Given an image embedding of an object and a single-word adjective, apply the adjective to the image embedding, altering its characteristics accordingly. |
|
|
|
|
| ## Inference |
| See the [pOps repo](https://github.com/pOpsPaper/pOps) for inference using the pretrained models |
|
|
|
|
