Skip to content

Releases: lucidrains/transfusion-pytorch

0.0.40

15 Sep 14:49

Choose a tag to compare

Full Changelog: 0.0.39...0.0.40

0.0.39

13 Sep 15:10

Choose a tag to compare

able to return predicted flow for modality only forward

0.0.38

13 Sep 14:05

Choose a tag to compare

allow for any modality to be separately trained

0.0.37

11 Sep 17:45

Choose a tag to compare

just give text its own forward for the AdaptiveWrapper as well

0.0.36

11 Sep 17:18

Choose a tag to compare

create a separate forward for language model pretraining

0.0.35

11 Sep 15:10

Choose a tag to compare

make sure prompting works, and force tests to start off with modality…

0.0.34

10 Sep 18:15

Choose a tag to compare

What's Changed

New Contributors

Full Changelog: 0.0.33...0.0.34

0.0.33

09 Sep 16:11

Choose a tag to compare

start applying unet skip connections in transformer settings more bro…

0.0.32

09 Sep 15:48

Choose a tag to compare

prepare for mixing different encoded shapes (audio, video) into the mix

0.0.31

09 Sep 14:44

Choose a tag to compare

get the overall logic of key value caching working, hide behind a fla…