Zecheng Tang
Zecheng Tang
Hi, it seems that the CUDA version of googlecolab mismatches with ours. For more solution, [https://github.com/NVIDIA/NeMo/issues/3176](https://github.com/NVIDIA/NeMo/issues/3176) may help.
> Latent dim is 4. And we will train a 16 version. Do not need repeat image, just input a image with the shape of 1 x 1 x 3...
Hi, you should open the graphical interface through the URL for interactive operation since our system is implemented based on the ``gradio``.
Hi, have you followed our ``download.sh`` file to download and implement the ControlNet models?
That is a strange question. Your error is reported in line 247of the code, but the purpose of this line is to load the model. Since you can successfully use...
Hi, have you installed ``transformers==4.26.1``? Make sure you install the same version with us.
Hi, have you followed our ``download.sh`` and ``requirement.txt`` to implement our code?
> Yes I did follow the readme steps In your ``download.sh``, making sure you have run the following code: ```shell git clone https://github.com/lllyasviel/ControlNet.git ln -s ControlNet/ldm ./ldm ``` You can...
Hi, actually you can just download the needed model ckp again and specify your ``ckp path`` when loading ckp with ``from_pretrained()`` method.
Hi, I can provide these two suggestions below: 1) You can install each package independently without utilizing the requirement.txt; 2) It seems that you utilize the ``mirrors.tencentyun.com`` for installment acceleration,...