Loading components for the flux1-dev checkpoint Huggingface

[VTaPo]

I cannot loading components for the flux1-dev checkpoint.

Here is my code:
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()
pipe.to(torch.float16)
prompt = "Create a commercial poster for restaurant"
out = pipe(
prompt=prompt,
guidance_scale=3.5,
height=768,
width=768,
num_inference_steps=1,
).images[0]
out.save("image.png")

The process always stops when 20% loading.
I have 40GB CPU RAM and 24GB VRAM on RTX3090.

[everythoughthelps]

pip install accelerate

[VTaPo]

@everythoughthelps Of course I did. However, every time I run the code as I provided, the loading components always stops at 20%. Is it possible that my configuration is not enough for using Flux1-dev from diffusers.

My requirements.txt file:
torch
torchvision

tokenizers
transformers
diffusers
accelerate
sentencepiece
bitsandbytes

numpy