RuntimeError: torch.cat(): expected a non-empty list of Tensors

byrkbrk commented 4 months ago

Describe the bug

Problem: When the "officially provided" example (see https://github.com/huggingface/diffusers/blob/a785992c1d6fcb1ff66f8a0d68d09a0a81b909e8/src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py#L34) is executed, the error occurs.

Expected behaviour: The example should work without any error.

Reproduction

The Code:

import torch
from diffusers import LEditsPPPipelineStableDiffusion
from diffusers.utils import load_image

if __name__ == "__main__":
    pipe = LEditsPPPipelineStableDiffusion.from_pretrained(
        "runwayml/stable-diffusion-v1-5",
        torch_dtype=torch.float16)
    pipe = pipe.to("mps")
    img_url = "https://www.aiml.informatik.tu-darmstadt.de/people/mbrack/cherry_blossom.png"
    image = load_image(img_url).convert("RGB")

    _ = pipe.invert(image=image, num_inversion_steps=50, skip=0.1)
    edited_image = pipe(
        editing_prompt=["cherry blossom"], 
        edit_guidance_scale=10.0, 
        edit_threshold=0.75).images[0]

The Error:

Traceback (most recent call last):
  File "/Users/burakbayrak/folder-to-del/leditsplusplus_example.py", line 16, in <module>
    edited_image = pipe(
                   ^^^^^
  File "/Users/burakbayrak/anaconda3/envs/ledits-plus-plus/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/burakbayrak/anaconda3/envs/ledits-plus-plus/lib/python3.11/site-packages/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py", line 1010, in __call__
    out = self.attention_store.aggregate_attention(
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/burakbayrak/anaconda3/envs/ledits-plus-plus/lib/python3.11/site-packages/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py", line 128, in aggregate_attention
    out = torch.stack([torch.cat(x, dim=0) for x in out])
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/burakbayrak/anaconda3/envs/ledits-plus-plus/lib/python3.11/site-packages/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py", line 128, in <listcomp>
    out = torch.stack([torch.cat(x, dim=0) for x in out])
                       ^^^^^^^^^^^^^^^^^^^
RuntimeError: torch.cat(): expected a non-empty list of Tensors

Logs

No response

System Info

🤗 Diffusers version: 0.29.2
Platform: macOS-14.5-arm64-arm-64bit
Running on a notebook?: No
Running on Google Colab?: No
Python version: 3.11.9
PyTorch version (GPU?): 2.3.1 (False)
Flax version (CPU?/GPU?/TPU?): not installed (NA)
Jax version: not installed
JaxLib version: not installed
Huggingface_hub version: 0.23.4
Transformers version: 4.42.3
Accelerate version: 0.32.1
PEFT version: not installed
Bitsandbytes version: not installed
Safetensors version: 0.4.3
xFormers version: not installed
Accelerator: Apple M2
Using GPU in script?: True
Using distributed or parallel set-up in script?: False

Who can help?

@yiyixuxu

a-r-r-o-w commented 4 months ago

Probably relevant: https://github.com/huggingface/diffusers/pull/6074#issuecomment-1997507552

cc @manuelbrack @kathath

github-actions[bot] commented 2 months ago

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

a-r-r-o-w commented 6 days ago

Gentle ping @manuelbrack @sayakpaul. cc @vladmandic

huggingface / diffusers