How to run this

[AkarshanGupta]

Any one have idea how to run this ??

[Ali-Flt]

Did you even read the README?

[AkarshanGupta]

Did you even read the README?

I recently downloaded both the 64x64 diffusion model and the corresponding classifier model. I've written interface code to call and integrate these two models, but I'm not getting any output. I'm finding the process a bit confusing and would greatly appreciate any guidance or assistance to resolve this issue.

[Ali-Flt]

running this command from the README should generate a .npz file including the sampled images. You can modify the image_sample.py code if you want to store the samples differently.

python scripts/image_sample.py --model_path /path/to/model.pt $MODEL_FLAGS $DIFFUSION_FLAGS

[AkarshanGupta]

running this command from the README should generate a .npz file including the sampled images. You can modify the image_sample.py code if you want to store the samples differently.

python scripts/image_sample.py --model_path /path/to/model.pt $MODEL_FLAGS $DIFFUSION_FLAGS

To clarify, I need to download the ZIP file, extract it, and run the code in an IDE (such as PyCharm or VS Code). After setting everything up, I can execute the command to generate the images. Is that correct?

[Ali-Flt]

You should:

1. Create a python environment (if you don't know how look it up it's easy)
2. In your created environment install this repository: pip install -e .
3. Download the checkpoint file for the model you want to run from the [checkpoint] links given in this section
4. Activate your created python environment and run python scripts/image_sample.py --model_path /path/to/model.pt $MODEL_FLAGS $DIFFUSION_FLAGS (Edit path to model and set your running arguments before running it). The running arguments should be set based on the model. Read this section