Comar
Comar
Thank you for your incredible work. Now, I'm trying to run train code with RTX 3090 (24GB). But, Even with batch size 1, I met out of memory exception, and...
Hi, thank you for your great work. I hava a question for the ControlNet training I am just trying to train ControlNet with canny edge condition using OpenImage Dataset to...
Hi, thank you for your awesome pruning work. I have had hard time to fix an issue. I just followed the sample code you offers in #6. After pruning, "pruend_macs,...
I am reaching out to share our recent intriguing findings from a compression experiment. Our results demonstrate a significant reduction in model size without compromising quality. Briefly, we discovered that...
Hi, thank you for awesome work. I'm interested in the theoretical contents in the original paper, and taking hard time to understand and derivate the equation 17. Can you explain...
Hi, thank you for your great work. While studying the implementations, I noticed some differences in the code compared to the paper, so I would like to ask some questions....
I found some extremely high camera parameters, which maybe is error, at 1K/48aaed5a44005bccd51d529ab90335b144fe5e7f3c8a22ba399f4ee3b3fb6728/. 
I found that the kernel size, which is described as $K=3$ in the paper, is set to 1 in depth generation. Could I know the reason you set the value...
Hello, Thank you for the invaluable work. I have a simple question. Is CogvideoX-I2V model finetuned from CogvideoX-T2V model or is it trained from scratch?