retrieval-augmented-diffusion-models
retrieval-augmented-diffusion-models copied to clipboard
Official codebase for the Paper “Retrieval-Augmented Diffusion Models”
Hi, Thanks for the great work. Which dataset was used for the pre-trained LDM? And which checkpoint was used and is it from here (?): https://github.com/CompVis/latent-diffusion Also is it the...
What is the idea behind the unimplemented `conditional_retrieval_encoder` [here](https://github.com/CompVis/retrieval-augmented-diffusion-models/blob/1017f2b51d43ff530f178c72c460bbba83316da6/rdm/models/diffusion/ddpm.py#L811)? Would this be another encoder to combine the CLIP embs of the original text query and KNNs?