Results 21 issues of ZeeLyn

### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmagic/issues) and [Discussions](https://github.com/open-mmlab/mmagic/discussions) but cannot get the expected help. - [X] I have read the [FAQ documentation](https://mmagic.readthedocs.io/en/latest/faq.html) but cannot get the expected help....

kind/bug

```shell [W 240323 12:00:44 _wdaproxy:65] [00008101-001A350A36D0001E] Unknown exception: request() got an unexpected keyword argument 'chunked' [E 240323 12:00:44 _wdaproxy:153] [00008101-001A350A36D0001E] wda started failed [D 240323 12:00:44 _wdaproxy:134] [00008101-001A350A36D0001E] launch WDA...

![image](https://github.com/Doubiiu/DynamiCrafter/assets/17895675/41c077aa-6dee-43d1-8f17-bf17fddd7a94)

Where is the tensorboard log file directory?

@2881099 我批量动态生成了多个id, 希望通过push方法一次添加到list里面去,通过以下方式调用,直接把数组序列化写入了,而不是多条: ![image](https://github.com/user-attachments/assets/aefd2db3-0520-4ecc-9037-a376cc34be37) 写入结果: ![image](https://github.com/user-attachments/assets/e3cb4004-326e-434a-9a6a-41d934384c75) 通过以下方式调用又可以写入多条 ```csharp await redis.RPushAsync($"wechat_video_spread:{data.Task}", 1,2,3); ``` 对于这种动态生成的数据我该如何调用?

生成的图像都是这样的

创建任务时同步返回任务ID

主机启动参数 ```bash accelerate launch --multi_gpu --num_machines=2 --machine_rank=0 --main_process_ip='localhost' --main_process_port=6600 ${launchArgs[@]} $trainer_file \ --enable_bucket \ --pretrained_model_name_or_path=$pretrained_model \ --ae=$ae \ --clip_l=$clip_l \ --t5xxl=$t5xxl \ --train_data_dir=$train_data_dir \ --output_dir="./output" \ --logging_dir="./logs" \ --log_prefix=$output_name \...

editor进行场景的缩放(ctrl+滚轮)时,有没有什么方式可以控制部分元素一直固定大小,不跟随一起缩放?

如果不需要那么高的fps,应该如何修改?