I was curious to try this model but I couldn't load it with diffusers.

Loading model /tmp/dpoxlplus.safetensors

Traceback (most recent call last):

File "/home/freitag/src/sd/gen/gen.py", line 322, in <module>

g = Gen(conf)

File "/home/freitag/src/sd/gen/gen.py", line 122, in init

self.pipe = StableDiffusionXLPipeline.from_single_file(

File "/home/freitag/py/lib/python3.10/site-packages/diffusers/loaders/single_file.py", line 261, in from_single_file

pipe = download_from_original_stable_diffusion_ckpt(

File "/home/freitag/py/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py", line 1694, in download_from_original_stable_diffusion_ckpt

text_encoder = convert_ldm_clip_checkpoint(checkpoint, local_files_only=local_files_only)

File "/home/freitag/py/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py", line 816, in convert_ldm_clip_checkpoint

set_module_tensor_to_device(text_model, param_name, "cpu", value=param)

File "/home/freitag/py/lib/python3.10/site-packages/accelerate/utils/modeling.py", line 269, in set_module_tensor_to_device

new_module = getattr(module, split)

File "/home/freitag/py/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1688, in getattr

raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'")

AttributeError: 'CLIPTextModel' object has no attribute 'text_projection'