Multimodal {Images, Text}->Text models using CLIP, GPT* and knn indices with indirect integration.
(WIP)
dalle-lightning and DALLE-datasets repos from which webdataset implementations are derived from.
Multimodal {Images, Text}->Text models using CLIP, GPT* and knn indices with indirect integration.
(WIP)
dalle-lightning and DALLE-datasets repos from which webdataset implementations are derived from.