Zhuoheng Li

> @StarCycle Yes we are working on a PR using `accelerate`: #317 Nice!

Hi @Cadene, Are there other things that I need to complete to merge this PR? (ﾉ"◑ڡ◑)ﾉ

The dataset is generated by the following `lmdb_format.py` ``` import gc import shutil from pathlib import Path import lmdb from pickle import loads from torchvision.io import decode_jpeg import numpy as...

Hello @jayLEE0301 @notmahi , I test diffusion policy using final IoU (following your settings). I load the official checkpoint, evaluate the Diffusion Policy with Unet for 20 episodes and get...

Hello @jayLEE0301 , Thank you for your response! - I always use `reward = np.clip(coverage, 0, 1)` instead of `reward = np.clip(coverage / self.success_threshold, 0, 1)` in my test. -...

Hi @zRzRzRzRzRzRzR But as you mentioned in your paper, you already have an image-to-video version of CogVideoX 

Hi @tengjiayan20, Thank you for the response! Is it difficult to finetune an image-to-video model by myself on the [WebVid10M](https://huggingface.co/datasets/TempoFunk/webvid-10M) dataset? How many samples and trainning steps do you need...

@Maikauer Yes, the open-source version does not support image2video at this moment. If there is an open-source strong I2V model, there will be a community finetuning it (like Stable Diffusion...