"Towards Enhanced Controllability of Diffusion Models. (arXiv:2302.14368v1 [cs.CV])" — Creating a diffusion model that is easier to edit/style based on input images by conditioning the model on a spatial content mask and a flattened style embedding.

Paper: http://arxiv.org/abs/2302.14368

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Comparison of the proposed mode…