jimmysue closed an issue on mir-group/allegro

January 7, 2025 8:01am

Inconsistency Between VAE Types in Pretrained Model and `single_inference.py`

I downloaded a pretrained model from Hugging Face with the intention of using single_inference.py for sampling. However, I noticed a discrepancy between the VAE types: the code in single_inference....

jimmysue opened an issue on rhymes-ai/Allegro

January 7, 2025 8:00am

Inconsistency Between VAE Types in Pretrained Model and single_inference.py

I downloaded a pretrained model from Hugging Face with the intention of using single_inference.py for sampling. However, I noticed a discrepancy between the VAE types: the code in single_inference....

jimmysue opened an issue on mir-group/allegro

January 7, 2025 7:57am

Inconsistency Between VAE Types in Pretrained Model and `single_inference.py`

I downloaded a pretrained model from Hugging Face with the intention of using single_inference.py for sampling. However, I noticed a discrepancy between the VAE types: the code in single_inference....

jimmysue opened an issue on PKU-YuanGroup/Open-Sora-Plan

January 7, 2025 7:47am

为什么采样出来的视频是倒放的？

下载了 1.3 版本的模型，使用 opensora/sample/sample.py 进行采样， 出来的结果是倒放的为什么？ 下面是一个生成的例子： https://github.com/user-attachments/assets/a9dfac11-fbb4-41f8-8db3-a36540deda1b 下面是我运行的参数配置： ``` "--master...