running out of memory on introduction_to_stablediffusion.ipynb

The issue is in introduction_to_stablediffusion.ipynb, specifically the cell running base and refiner models. Start by checking GPU memory usage in Colab with a T4. Look at the model loading and inference steps; consider reducing batch size, image resolution, or using memory optimization techniques like gradient checkpointing. The error trace points to a conv2d operation in PyTorch. Verify the environment variables like PYTORCH_CUDA_ALLOC_CONF. Running the notebook step-by-step and monitoring memory with torch.cuda.memory_summary will help identify the peak usage.

Thanks for this notebook @rkdan ! This is great!

In introduction_to_stablediffusion.ipynb running on Google Colab with an instance of a T4 GPU, I am running out of memory.

https://github.com/acceleratescience/diffusion-models/blob/main/notebooks/introduction_to_stablediffusion.ipynb

My code is here:

https://github.com/neelsoumya/diffusion-models/blob/main/notebooks/introduction_to_stablediffusion.ipynb

I can run until here (where I get an error):

# run both experts
image_base = base(
    prompt=prompt,
    num_inference_steps=n_steps,
    denoising_end=high_noise_frac,
    output_type="latent",
).images

image_final = refiner(
    prompt=prompt,
    num_inference_steps=n_steps,
    denoising_start=high_noise_frac,
    image=image_base,
).images[0]

Error message is

---------------------------------------------------------------------------
OutOfMemoryError                          Traceback (most recent call last)
<ipython-input-8-410c6a79b4f8> in <cell line: 0>()
      7 ).images
      8 
----> 9 image_final = refiner(
     10     prompt=prompt,
     11     num_inference_steps=n_steps,

17 frames
/usr/local/lib/python3.11/dist-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight, bias)
    547                 self.groups,
    548             )
--> 549         return F.conv2d(
    550             input, weight, bias, self.stride, self.padding, self.dilation, self.groups
    551         )

OutOfMemoryError: CUDA out of memory. Tried to allocate 512.00 MiB. GPU 0 has a total capacity of 14.74 GiB of which 306.12 MiB is free. Process 6006 has 14.44 GiB memory in use. Of the allocated memory 14.17 GiB is allocated by PyTorch, and 145.94 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)

My code is here:

https://github.com/neelsoumya/diffusion-models/blob/main/notebooks/introduction_to_stablediffusion.ipynb