DisCo
DisCo copied to clipboard
Wangt-CN
[CVPR2024] DisCo: Referring Human Dance Generation in Real World
Hi, thanks for your great work! When do you release the model checkpoint for temporal module? Hope for it early.
Tanks for your awesome work. Do you know how to fix the 'Nan' loss in training and the results is black in inference.
When I run the google colab DisCo_Demo.ipynb, the following error occurred. ``` --------------------------------------------------------------------------- ModuleNotFoundError Traceback (most recent call last) [](https://localhost:8080/#) in () 4 5 from utils.wutils_ldm import * ----> 6...
Is this xformers necessary pip install xformers failed，so I delete code related to xformers，but get result like:  
A part of my environment for DisCo_Demo.ipynb is as follows: ``` !pip list ... ... deepspeed 0.8.2 ... ... ``` But the following error occurred. ``` [2023-10-24 06:36:41 ] :...
I used the jupyter file you provided and changed to py to run it, but the results were very poor as shown in the video below: Original pose video： https://github.com/Wangt-CN/DisCo/assets/143077425/fb33744d-57c8-4ee3-83e9-09c9dbd3f92d...
Your work is very good, I would love to experience your work, but found that the URL does not open, can you open it for a while?
Hi ! Thanks for your Disco paper and explanation for the TSV file preparation. In the composite yaml file, you have a 'caption linelist' file which is used. caption_linelist: train_TiktokDance-coco-single_person-Lindsey_0411_youtube-SHHQ-1.0-deepfashion2-laion_human-masks-single_cap.caption.linelist.tsv...
Hello, thank you for the great code. However, I have some slight concerns about the image quality, so I wanted to ask if it's possible to replace the sd-image-variations-diffusers model...
AttributeError: 'DDPMScheduler' object has no attribute 'remove_noise'
