Open Muqeeth99 opened 1 year ago
min-dalle uses three models in the pipeline to generate images from text.
There are two variants of the pipeline
Variant | Size Details |
---|---|
mini | encoder - 386 MB, decoder - 448 MB, detokenizer - 178 MB |
mega | encoder - 2.06 GB, decoder - 2.75 GB, detokenizer - 178 MB |
VQGAN Detokenizer is same in both variants.
What is the size of this model of min-dalle?