andreas

We did not implement it for DDIM. You could modify the original DDIM method by following this [code overview](https://github.com/andreas128/RePaint#code-overview). Are you still working on it?

To get the same commit as we used do the following: ``` git clone https://github.com/openai/guided-diffusion.git cd guided-diffusion git checkout 912d577 ``` For training we use 256 × 256 crops in...

Please follow this [guide](https://github.com/andreas128/RePaint#details-on-data). Does that work for you?

The following command should download the model. Does that work for you? ``` pip install --upgrade gdown && bash ./download.sh ``` Alternatively this is the google drive link for `celeba256_250000.pt`:...

It seems that the model architecture has changed. Try to use the model code from your training by copying it [here](https://github.com/andreas128/RePaint/blob/main/guided_diffusion/unet.py). Does that work?

Does this [answer](https://github.com/andreas128/RePaint/issues/6) help?

You need to train using the original guided-diffusion code base. To get the same commit as we used do the following: ``` git clone https://github.com/openai/guided-diffusion.git cd guided-diffusion git checkout 912d577...

Does the following work for you? **1. Download the models** ``` pip install --upgrade gdown && bash ./download.sh ``` **2. Apply it to the LaMa data** Use the following configs...