question about load sanapipeline

[LearningHx]

pipe = SanaPipeline.from_pretrained(
"Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers",
variant="bf16",
torch_dtype=torch.bfloat16,
)
I encountered an error when loading the model with the code above：OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory /home/ma-user/work/hexiao/Sana-main_distillation/weights/Sana_600M_512px-diffusers/text_encoder.

I found the pretrained text encoder in huggingface named model-00001-of-00002.safetensors and model-00002-of-00002.safetensors. I want to know what these two weights represent and how I should modify the code to load the model correctly

[lawrence-cj]

run pip install git+https://github.com/huggingface/diffusers before use Sana in diffusers

import torch
from diffusers import SanaPipeline

pipe = SanaPipeline.from_pretrained(
    "Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers",
    variant="bf16",
    torch_dtype=torch.bfloat16,
)

What's your diffusers version

[LearningHx]

I have installed diffusers==0.32.1

[lawrence-cj]

You may need to upgrade your hunggaface_hub, transformers lib simultaneously.
I haven't met the same problem before.
You don't need to modify any weight.