Junjie

Can the model reach the loss value and accuracy given in the paper?

3

Can the model reach the values given in the paper with backbone network is MobileNet, VGG16, Inception-V2 respectively. And according to my experiments, It can not. So I wonder if...

Some questions to produce good generation results.

1

Hi, thank you very much for sharing your clean implementation. I would like to ask you some questions: 1. How much data we need to produce a good generation result....

The dataset link of Baidu cloud disk is invalid.

1

The dataset link of Baidu cloud disk is invalid. Can you fix it? Thank you.

Java apt ppa resource is no longer valid.

1

Maybe you should change `sudo add-apt-repository ppa:webupd8team/java` to `sudo add-apt-repository ppa:ts.sch.gr/ppa`. I have tested this source, it worked.

I want to use datapipe to read parquet files in which image is stored as binary. But I got error: ``` NotImplementedError: Unsupported Arrow type: binary ``` So I wonder...

I have noticed that under the global loss setting, when training with multiple nodes, the GPU memory usage will be much higher than when training with a single node. So,...

Could you please provide the fivek training set? I cannot handle process raw data without lightroom. Can you provide your training data (maybe jpg or png)? Thank you in advance.

The advantage compared with ConsiStory.

5

Hi, StoryDiffusion is a nice work about customized generation and thanks for the open source code. Can you describe the differences and advantages between the proposed CSA and ConsiStory [1]...

when will the code be released

5

s2cnet is a nice work. i wonder when will the code be released ? Thanks in advance.

[Bug]: Data Parallel with embed task hangs.

1

### Your current environment Output of `python collect_env.py`: ```shell PyTorch version: 2.6.0+cu124 Is debug build: False CUDA used to build PyTorch: 12.4 ROCM used to build PyTorch: N/A OS: Ubuntu...