Wenhao Wang

About the license for the pre-trained model

1

Thanks for the great work! The database is released under an MIT license. I want to know whether the pre-trained models are also released under the MIT license? Thanks.

A million-scale text-to-video prompt-gallery dataset

5

Hi, We contribute the first dataset featuring 1.67 million unique text-to-video prompts and 6.69 million videos generated from 4 different state-of-the-art diffusion models. We hope it can help your Open-Sora...

A million-scale text-to-video prompt-gallery dataset

1

Hi, We contribute the first dataset featuring 1.67 million unique text-to-video prompts and 6.69 million videos generated from 4 different state-of-the-art diffusion models. We hope it can help your Open-Sora...

Thanks for the interesting work you have done. However, I have some questions about performance. In your paper, you say the performance of MEB-Net is 76.0%, which is much better...

More Feature

1

Could you integrate our [3st Place Solution of the Facebook AI Image Similarity Challenge](https://github.com/WangWenhao0716/ISC-Track2-Submission) into your repo? This is a very easy and well-generalized version of our [1st Place Solution...

Thanks for this excellent work. When I try to run it on multi-nodes with 16 GPUs, there is an error: ``` Traceback (most recent call last): File "/gs/home/statchao/zdhu/code/DiT_wenhao/DiT/train.py", line 271,...

Sorry, I cannot open the link of form. Can you give me another way to submit the form?