Muyao Niu
Muyao Niu
> My CUDA version is 12.1. > > 1.pip install cupy-cuda12x. 2.conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.8 -c pytorch -c nvidia. > > To modify compile_with_cache function: > > *...
Could you tell me which input form do you want? We are providing the gradio because it is the easiest way to form the input via line drawing.
You might find it helpful to look at this line of code: https://github.com/MyNiuuu/MOFA-Video/blob/main/MOFA-Video-Traj/run_gradio.py#L570. You can adjust the codes by isolating this function and providing your own input to the function.
那个demo还在调试中，主要的原因是因为huggingface的ZeroGPU模块无法支持cupy，所以现在的版本还没有办法跑通，我已经向官方进行了反馈，但是可能需要等一段时间
Hi! Thanks for your interest! To make the model work with only motion flow inputs, you'll need to retrain it. The current model relies on both motion flow and landmarks,...
We have uploaded the training code.
Sorry, but this work was done during my internship at Tencent AI Lab. Since I have left the company, I can no longer access the data files stored on their...
We trained the model for approximately 100,000 iterations using the WebVid-10M dataset, with a batch size of 8 (one per A100 GPU). This means a total of about 800,000 video...
> > We trained the model for approximately 100,000 iterations using the WebVid-10M dataset, with a batch size of 8 (one per A100 GPU). This means a total of about...
> different The Encoder in Figure 3 is a part of the Controlnet it self, which is called 'Fusion Encoder', which is illustrated in Figure 3 and the text. The...