VEnhancer

VEnhancer copied to clipboard

DQYZHWK

Unable to get the same resolution

7

https://github.com/user-attachments/assets/8c65fa06-84b8-4201-8126-fb053f263c16 When i try to enhance the video above from open-sora the target resolution is always set to a max of 1152, 2048 2024-10-14 01:59:38,941 - video_to_video - INFO -...

SamitM1

Why is the character's identity poorly maintained?

3

this is my execution command： python enhance_a_video.py --version v2 \ --up_scale 2 --target_fps 24 --noise_aug 100 \ --solver_mode 'fast' --steps 15 \ --input_path prompts_v3 \ --prompt_path prompts_v3/text_prompts_v3.txt \ --save_dir 'results/'...

zzk88862

yea as a title say, is it possible to train the checkpoint?

jungbtc

Cannot reproduce results using the same demo

1

Hi authors, I have used the v2 ckpts to try to reproduce your results but I cannot keep the fidelity as yours. The whole face changed a lot. Can you...

DDDaxing

有计划优化 VEnhancer 的训练和微调代码吗

1

DQYZHWK

Can you please provide Inference time benchmarks?

3

What is the time taken for processing a 3/5/10s video? on a A100/H100 GPU. Would be great to know any of your existing benchmarks!

cbsudux

OutOfMemoryError: CUDA out of memory with 24GB. Is it possible to apply torchao quantization?

16

I'm getting a OOM running the ```bash python enhance_a_video.py \ --version v2 \ --up_scale 4 --target_fps 24 --noise_aug 250 \ --solver_mode 'fast' --steps 15 \ --input_path 'prompts/' \ --prompt_path 'prompts/text_prompts.txt'...

loretoparisi

Approximate release date of MULTI-GPU inferencing

18

Hey guys great work with this. We were wondering if and (approximately) when you will be releasing the multi gpu inferencing. Furthermore what is the time taken with default settings...

SamitM1

Will you support multi-GPU tensor parallelism in the future?

4

I run this model on cloud server so I can choose to rent multi-GPU,it takes more than 1 hour to generate a video in 1 GPU and it doesn't get...

Willian7004