DisCo

DisCo copied to clipboard

No access to tiktok checkpoints

3

fatal: destination path 'sd-image-variations-diffusers' already exists and is not an empty directory. --2023-12-04 22:04:02-- https://storage.googleapis.com/disco-checkpoint-share/checkpoint_ft/moretiktok_nocfg/mp_rank_00_model_states.pt Resolving storage.googleapis.com (storage.googleapis.com)... 142.250.141.207, 142.251.2.207, 2607:f8b0:4023:c0d::cf Connecting to storage.googleapis.com (storage.googleapis.com)|142.250.141.207|:443... connected. HTTP request sent, awaiting...

JetsettingJames

There is sth wrong with ./annotator/grounded-sam/run.py

2

I modify the args and used python ./annotator/grounded-sam/run.py --dataset_root ./single/ --partition 1。 Under groundsam_vis folder，I got 001.png.mask.jpg and 001.png.mask.png. The original size of pic is 540*960, 001.png.mask.png is 540*960, but...

zhangtao22

Sample images of demo video request.

2

Thank you for the nice work, DisCo. I want to replicate your experiment. Can you share all the photos and pose samples in the demo video https://www.youtube.com/watch?v=alJKsj3JpBo? It's really hard...

yunseongcho

When sampling a segment of video to train the temporal module, the length of the dataset is divided by the `train_sample_interval = 4`. But in this line: https://github.com/Wangt-CN/DisCo/blob/8538889c9ee9edd8dd43ffee182d1a91ce7a9828/dataset/tiktok_video_dataset.py#L295 the code...

ljh0v0

Incorrect FID-VID and FVD

15

Thanks for great work. @Wangt-CN I tried to reproduce the results using "gen_eval.sh," but I noticed that the FID-VID and FVD do not match the results reported in the paper....

Fanghaipeng

@Wangt-CN Thanks to your great work! I have a few questions about the generated image sizes: 1. Using the pretraing model currently provided, can only 256*256 images be generated? 2....

ZZfive

Where can I get the 10K tiktok style test split?

Worromots

Very slow xformers install on the Colab

3

Hi, I'm trying to run the Colab linked on the readme of the repo, and in Step 2 on the last xformers line, it is taking a very long time....

ShawnFumo

This typo caused the frames not to be sampled correctly according to self.eval_sample_interval.

Fanghaipeng

for human-specific fine-tuning，I can't execute

3

I set my dataset like the toy_dataset you provided. However, it can't execute. I encountered this problem Original Traceback (most recent call last): File "/root/.local/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop data...

zhangtao22