motion-latent-diffusion

motion-latent-diffusion copied to clipboard

Hello, I've been trying your project, and it went successful on the t2m task. But I was wondering how to make use of the a2m models and configs that you've...

ou524u

Hello, thank you for providing such an excellent project! I encountered some issues while evaluating the performance of pretrained models on the HumanML3D dataset: I did not find 'Multimodal Dist'...

fyyakaxyy

Motion Representations

2

I noticed that you converted the rotation of the root node into other forms when expressing motion. May I ask how to convert the representation in the data set you...

cyk990422

Hi, I trained from scratch the VAE and diffusion modules on the KIT dataset. I followed your instructions and: - downloaded the processed data from HumanML3D - changed only the...

nefeliandreou

Hi, Is it possible to generate a single character from the Pose for about 5 seconds? I have a video of Pose ( openpose + hands + face) and i...

p0mad

Where is action-to-motion code?

xwg0508

您好： 按照Readme文档运行text-to-motion的时候（前面模型已经按照脚本下载完毕），但是在运行：python demo.py --cfg ./configs/config_mld_humanml3d.yaml --cfg_assets ./configs/assets.yaml --example ./demo/example.txt --task text_motion的时候，在get_data处报错，这里需要先预处理好humanml3D的数据吗？如果不需要，我怎样才能顺利生成？

Theweekfoolish229

Demo.py Frame Rate and Number of Generated Samples

4

Hi I have two questions. 1- Is it possible to know the default frame rate used for generation of actions? I could see that frame rate is defined in multiple...

mmdrahmani

Can you provide instructions for other datasets such as UESTC and HumanAct12?

2

Thank you very much for open-sourcing the code. Here, I would like to inquire if it would be possible to provide more information about the Action to Motion task, such...

Xuguowei-hub

你好，我在你的页面找到了你在action-to-motion任务中，HumanAct12数据集下的预训练模型，请问action-to-motion任务在UESTC数据集的预训练模型在哪里可以找到？还有evaluate的代码好像没有关于action-to-motion任务的，期待你的回复，谢谢！

maweizhao