"Modulating Pretrained Diffusion Models for Multimodal Image Synthesis. (arXiv:2302.12764v1 [cs.CV])" — Multimodal Conditioning Modules (MCM) for enabling conditional image synthesis using pretrained diffusion models so that you can generate images using not just a text prompt, but additional input such as a segmentation map or a sketch.

Paper: http://arxiv.org/abs/2302.12764

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Multimodal conditioning modules…