Edwardmark
Edwardmark
@mmaaz60 hi could you tell me what is the inference speed of your model? and how to do batch inference to improve the efficiency? Thanks.
@JustinLJun 百度云的数据在哪儿下载呢？没找到 多谢
@glenn-jocher I am a little confused about evolve, is it used for training or just find the hyperparameters by train a few epochs and then use the hyp found to...
大家对虹膜识别有兴趣的也可以给我发邮件，我们建个群一起讨论下。
I test the open-sourced checkpoint the repo provided is unstable and shaking too. Is there anything missing? I run the demo using: torchrun --standalone --nproc_per_node=8 scripts/opensora/sample_opensora.py \ --model_time_scale 1 \...
@oahzxl why sp size should be as small as possible?
Specifically, when I set num_frames to 68, the t in stdit_block is 20, I cannot understand why is that. self.micro_frame_size = 17, why we need to use this setting 17?...
> do u find why? no, it is so strange to set to 17.
@sarroutbi @vjandrea @mahone3297 @duguyixiaono1 could you explain a bit? Thanks.
@zhengzangw could you give me a hint why we set vae micro-batch to 17? When I change it to 16, the video generated is really strange with sudden change.