FluxPipeline Error: Trying to set a tensor of shape torch.Size([3072]) in "bias" (which has shape torch.Size([576])), this looks incorrect.

[ReppiksProductions]

Greetings,
I've been trying to setup a CLI script to run FLUX.1-dev to generate images to test LORAs. I am interested in it because I prefer not to have to load up a large GUI for doing simple sample images.

I was having issues with my script so I decided to try out the example on the homepage of the FluxPipeline. When I run my script as well as the FluxPipeline example I get the following error: ValueError: Trying to set a tensor of shape torch.Size([3072]) in "bias" (which has shape torch.Size([576])), this looks incorrect.

Here is my Traceback:

A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "E:_python_projects\gen_img_diffusers_v9\env\lib\site-packages\xformers_init_.py", line 57, in _is_triton_available
import triton # noqa
ModuleNotFoundError: No module named 'triton'
Loading pipeline components...: 29%|██████████████▊ | 2/7 [00:00<00:00, 28.57it/s]
Traceback (most recent call last):
File "E:_python_projects\gen_img_diffusers_v9\test.py", line 6, in
pipe = FluxPipeline.from_pretrained("C:_Python Projects\StableDiffusionModels\Full\FLUX.1-Dev", torch_dtype=torch.bfloat16)
File "E:_python_projects\gen_img_diffusers_v9\env\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "E:_python_projects\gen_img_diffusers_v9\env\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 896, in from_pretrained
loaded_sub_model = load_sub_model(
File "E:_python_projects\gen_img_diffusers_v9\env\lib\site-packages\diffusers\pipelines\pipeline_loading_utils.py", line 704, in load_sub_model
loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
File "E:_python_projects\gen_img_diffusers_v9\env\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "E:_python_projects\gen_img_diffusers_v9\env\lib\site-packages\diffusers\models\modeling_utils.py", line 886, in from_pretrained
accelerate.load_checkpoint_and_dispatch(
File "E:_python_projects\gen_img_diffusers_v9\env\lib\site-packages\accelerate\big_modeling.py", line 613, in load_checkpoint_and_dispatch
load_checkpoint_in_model(
File "E:_python_projects\gen_img_diffusers_v9\env\lib\site-packages\accelerate\utils\modeling.py", line 1780, in load_checkpoint_in_model
set_module_tensor_to_device(
File "E:_python_projects\gen_img_diffusers_v9\env\lib\site-packages\accelerate\utils\modeling.py", line 286, in set_module_tensor_to_device
raise ValueError(
ValueError: Trying to set a tensor of shape torch.Size([3072]) in "bias" (which has shape torch.Size([576])), this looks incorrect.

This is my python code:

`import torch
from diffusers import FluxPipeline

model_id = "C:_Python Projects\StableDiffusionModels\Full\FLUX.1-Dev" #you can also use black-forest-labs/FLUX.1-dev

pipe = FluxPipeline.from_pretrained("C:_Python Projects\StableDiffusionModels\Full\FLUX.1-Dev", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU power

prompt = "A cat holding a sign that says hello world"
seed = 42
image = pipe(
prompt,
output_type="pil",
num_inference_steps=4, #use a larger number if you are using [dev]
generator=torch.Generator("cpu").manual_seed(seed)
).images[0]
image.save("flux-schnell.png")`

I'm using Python 3.10.11
Pytorch 2.5.1+cu124
Diffusers 0.32.0.dev0 (I started with 0.31.0 but downloaded latest hoping it would fix my issue)