Releases: lucidrains/video-diffusion-pytorch
Releases · lucidrains/video-diffusion-pytorch
0.0.9
offer means for attending to the present
0.0.8
complete relative positional encoding for attention across time throu… …gh attention bias
0.0.7
make it even easier
0.0.6
add Attention across Time after all (spatial) linear attention
0.0.4
actually use classifier free guidance during sampling, using the cond… …_scale > 1
0.0.2
attend to space and time
0.0.1
modify unet to be all conv3ds, complete all spatial attention, but te… …mporal attention still to be done