Hyo

Results 6 comments of Hyo

@zby-github @mks0601 I am facing the same problem. Could you please tell me how to solve it? Thanks!

@luluvi Could it be that your alignment method is different from that utilized in the original paper?

> We dont' have bandwidth to test that many CUDA versions. If you can change setup.py to compile for cu113 and test it please let us know. May I ask...

Hi, adjusting height may be not working. there are bugs when concatenating the output of downsampling and upsampling blocks. The shapes do not match. https://github.com/Doubiiu/DynamiCrafter/blob/ce86a1207494e11f7befda7bfb5235ea8f9d518e/lvdm/modules/networks/openaimodel3d.py#L596 Could you pls help to...

@scutpaul Looking forward to your fascinating models!!!!!!!!!

@Steven-SWZhang May I ask if is there any convenient way to obtain the starting image with the resolution of 1280x720? Now most of the t2i model can only generate images...