FGT issues

add models to Hugging Face Hub

2

Hi! Would you be interested in sharing your models in the [Hugging Face Hub](http://hf.co/models)? The Hub offers free hosting and it would make your work more accessible and visible to...

AK391

test own video , need mask?

1

If I want to test whether my video needs to correspond to the mask of each frame, in fact, I think the difficulty lies in obtaining the mask of each...

zhanghongyong123456

FGT++

5

I see FGT++ mentioned in the Readme. Is there any related code in the repo?

bhack

Add a way to extract an `ONNX` file

1

First of all, thanks a lot for this amazing project and your hard work! In https://github.com/burn-rs/burn we are trying to load different `ONNX` models, convert them into `burn` models, and...

Luni-4

About setting parameter batch_size=1, num_frames=5

3

In the second stage of the FGT network training, I found that batch_size was only set to 1 and only 5 frames per video were selected for training. Thus, the...

hwpengTristin

Outpainting Training on Custom Data

Good day, I am looking to train the outpainting model on a custom dataset, but I am not so sure what will be most effective. I was thinking about fine-tuning...

goME2448

Slow speed when inferencing

3

How to be faster by modify some params?

blahole

CUDA error

1

Hi, I got the following cuda error, I'm not sure what happening here: ``` RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors...

Xiaoyuan-Isaac-Wang

Watermark removal results is worse

run the Watermark removal on schoolgirls data using schoolgirls mask , but the results is worse, the imgs is not like backgroud just like some random color

Mr-Kyrie