FanJ

About details for evaluation

2

Thanks for your wonderful work! I have two questions about the evaluation: 1. if I want to directly utilize the pre-trained model for inference, do I need to do a...

Fail to download SAT 5B model

7

I also tried downloading CogVideoX-5B-transformer.tar.gz in file 1, but it cannot be unzipped correctly. Could you provide a way to get 5B transformer model for SAT? Thank you so much.

Hi, I encountered an error while running `transformer_model = OpenSoraT2V.from_pretrained(args.model_path, subfolder="93x720p", cache_dir=args.cache_dir, low_cpu_mem_usage=False, device_map=None, torch_dtype=weight_dtype). ` My bash command is ```bash python opensora/sample/sample_long_videos.py \ --model_path LanguageBind/Open-Sora-Plan-v1.2.0 \ --num_frames 93 \...

Where can I find the parameters for the v1.2 model that generates the best results

2

Just like the parser provided in v1.0.0 

While generating a 10-second video with CogVideoX-1.5, encountered (OOM) on machine with 80 GB of GPU memory.

5

### System Info / 系統信息 ```ruby Package Version ------------------------ ----------- accelerate 1.1.1 aiofiles 23.2.1 aiohappyeyeballs 2.4.3 aiohttp 3.10.10 aiosignal 1.3.1 annotated-types 0.7.0 antlr4-python3-runtime 4.9.3 anyio 4.6.2.post1 async-timeout 4.0.3 attrs 24.2.0...

Found black and white video when sampling CogVideoX1.5-5B 10s using code from huggingface.

5

### System Info / 系統信息 None ### Information / 问题信息 - [ ] The official example scripts / 官方的示例脚本 - [X] My own modified scripts / 我自己修改的脚本和任务 ### Reproduction /...