Can't run Automatic1111 WebUI with SDXL 1.0

[mashb1t]

Has this issue been opened before?

• It is not in the FAQ, I checked.
• It is not in the issues, I searched.

Describe the bug

It's not possible to load SDXL V1 with the latest release and after building the latest image.

Which UI

auto

Hardware / Software

• OS: Windows 10
• OS version: 22H2 (Build 19045.3208)
• WSL version (if applicable): version 2
• Docker Version: Docker version 24.0.2, build cb74dfc
• Docker compose version: Docker Compose version v2.19.1
• Repo version: latest, 09a0f11
• RAM: 128GB
• GPU/VRAM: NVidia RTX 4090, 24GB VRAM

Steps to Reproduce

1. Download SDXL safetensor model from https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main
2. load model
3. see error below

Additional context

2023-07-27 17:59:31 changing setting sd_model_checkpoint to base_sd/sd_xl_base_1.0.safetensors: RuntimeError
2023-07-27 17:59:31 Traceback (most recent call last):
2023-07-27 17:59:31 File "/stable-diffusion-webui/modules/shared.py", line 605, in set
2023-07-27 17:59:31 self.data_labels[key].onchange()
2023-07-27 17:59:31 File "/stable-diffusion-webui/modules/call_queue.py", line 13, in f
2023-07-27 17:59:31 res = func(*args, **kwargs)
2023-07-27 17:59:31 File "/stable-diffusion-webui/webui.py", line 226, in
2023-07-27 17:59:31 shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights()), call=False)
2023-07-27 17:59:31 File "/stable-diffusion-webui/modules/sd_models.py", line 556, in reload_model_weights
2023-07-27 17:59:31 load_model_weights(sd_model, checkpoint_info, state_dict, timer)
2023-07-27 17:59:31 File "/stable-diffusion-webui/modules/sd_models.py", line 286, in load_model_weights
2023-07-27 17:59:31 model.load_state_dict(state_dict, strict=False)
2023-07-27 17:59:31 File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2041, in load_state_dict
2023-07-27 17:59:31 raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
2023-07-27 17:59:31 RuntimeError: Error(s) in loading state_dict for LatentDiffusion:
2023-07-27 17:59:31 size mismatch for model.diffusion_model.input_blocks.4.1.proj_in.weight: copying a param with shape torch.Size([640, 640]) from checkpoint, the shape in current model is torch.Size([640, 640, 1, 1]).
2023-07-27 17:59:31 size mismatch for model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([640, 2048]) from checkpoint, the shape in current model is torch.Size([640, 768]).
2023-07-27 17:59:31 size mismatch for model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_v.weight: copying a param with shape torch.Size([640, 2048]) from checkpoint, the shape in current model is torch.Size([640, 768]).
2023-07-27 17:59:31 size mismatch for model.diffusion_model.input_blocks.4.1.proj_out.weight: copying a param with shape torch.Size([640, 640]) from checkpoint, the shape in current model is torch.Size([640, 640, 1, 1]).
2023-07-27 17:59:31 size mismatch for model.diffusion_model.input_blocks.5.1.proj_in.weight: copying a param with shape torch.Size([640, 640]) from checkpoint, the shape in current model is torch.Size([640, 640, 1, 1]).
2023-07-27 17:59:31 size mismatch for model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_k.weight: copying a param with shape torch.Size([640, 2048]) from checkpoint, the shape in current model is torch.Size([640, 768]).

...

[rahul1201dtu]

Facing this issue please help

Traceback (most recent call last):
File "d:\anaconda3\envs\tf\lib\threading.py", line 973, in _bootstrap
self._bootstrap_inner()
File "d:\anaconda3\envs\tf\lib\threading.py", line 1016, in _bootstrap_inner
self.run()
File "d:\anaconda3\envs\tf\lib\threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "D:\stable-diffusion-webui\modules\initialize.py", line 147, in load_model
shared.sd_model # noqa: B018
File "D:\stable-diffusion-webui\modules\shared_items.py", line 110, in sd_model
return modules.sd_models.model_data.get_sd_model()
File "D:\stable-diffusion-webui\modules\sd_models.py", line 499, in get_sd_model
load_model()
File "D:\stable-diffusion-webui\modules\sd_models.py", line 626, in load_model
load_model_weights(sd_model, checkpoint_info, state_dict, timer)
File "D:\stable-diffusion-webui\modules\sd_models.py", line 353, in load_model_weights
model.load_state_dict(state_dict, strict=False)
File "D:\stable-diffusion-webui\modules\sd_disable_initialization.py", line 223, in
module_load_state_dict = self.replace(torch.nn.Module, 'load_state_dict', lambda *args, **kwargs: load_state_dict(module_load_state_dict, *args, **kwargs))
File "D:\stable-diffusion-webui\modules\sd_disable_initialization.py", line 221, in load_state_dict
original(module, state_dict, strict=strict)
File "D:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 2041, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DiffusionEngine:
size mismatch for model.diffusion_model.out.2.weight: copying a param with shape torch.Size([4, 320, 3, 3]) from checkpoint, the shape in current model is torch.Size([9, 320, 3, 3]).
size mismatch for model.diffusion_model.out.2.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([9]).