stable-diffusion-webui icon indicating copy to clipboard operation
stable-diffusion-webui copied to clipboard
Published 1 week ago • verified publisher icon AUTOMATIC1111

[Bug]: Error upon loading SD3.5 medium

Open TriDefender opened this issue 1 year ago • 3 comments

Checklist

  • [x] The issue exists after disabling all extensions
  • [x] The issue exists on a clean installation of webui
  • [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
  • [X] The issue exists in the current version of the webui
  • [ ] The issue has not been reported before recently
  • [ ] The issue has been reported before but has not been fixed yet

What happened?

Tried to load \stableDiffusion35_medium_912387.safetensors, failed

Steps to reproduce the problem

Load webui Select model stableDiffusion35_medium_912387.safetensors

What should have happened?

WebUI should load correctly the model

What browsers do you use to access the UI ?

Google Chrome

Sysinfo

sysinfo-2024-11-01-23-02.json

Console logs

venv "C:\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.10.1
Commit hash: 82a973c04367123ae98bd9abdf80d9eda9b910e2
Installing sd-webui-controlnet requirement: changing opencv-python version from 4.10.0.84 to 4.8.0
removing nvidia-cudnn-cu11
Launching Web UI with arguments:
C:\stable-diffusion-webui\venv\lib\site-packages\timm\models\layers\__init__.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
  warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
No module 'xformers'. Proceeding without it.
CivitAI Browser+: Aria2 RPC started
2024-11-02 00:00:45,972 - ControlNet - INFO - ControlNet v1.1.415
ControlNet preprocessor location: C:\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads
2024-11-02 00:00:46,062 - ControlNet - INFO - ControlNet v1.1.415
Loading weights [ee6a527295] from C:\stable-diffusion-webui\models\Stable-diffusion\********************.safetensors
Creating model from config: C:\stable-diffusion-webui\configs\v1-inference.yaml
C:\stable-diffusion-webui\venv\lib\site-packages\huggingface_hub\file_download.py:797: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
  warnings.warn(
[ERROR]: Config states C:\stable-diffusion-webui\config_states\civitai_subfolders.json, "created_at" does not exist
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 16.0s (prepare environment: 5.2s, import torch: 3.5s, import gradio: 1.1s, setup paths: 0.8s, initialize shared: 0.2s, other imports: 0.5s, load scripts: 3.6s, create ui: 0.9s, gradio launch: 0.2s).
Applying attention optimization: Doggettx... done.
Model loaded in 4.8s (load weights from disk: 0.5s, create model: 0.3s, apply weights to model: 3.7s, calculate empty prompt: 0.2s).
Reusing loaded model kizukiAnimeHentai_animeHentaiV4.safetensors [ee6a527295] to load stableDiffusion35_medium_912387.safetensors [11fe06e223]
Loading weights [11fe06e223] from C:\stable-diffusion-webui\models\Stable-diffusion\stableDiffusion35_medium_912387.safetensors
Creating model from config: C:\stable-diffusion-webui\configs\sd3-inference.yaml
C:\stable-diffusion-webui\venv\lib\site-packages\huggingface_hub\file_download.py:797: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
  warnings.warn(
changing setting sd_model_checkpoint to stableDiffusion35_medium_912387.safetensors [11fe06e223]: RuntimeError
Traceback (most recent call last):
  File "C:\stable-diffusion-webui\modules\options.py", line 165, in set
    option.onchange()
  File "C:\stable-diffusion-webui\modules\call_queue.py", line 14, in f
    res = func(*args, **kwargs)
  File "C:\stable-diffusion-webui\modules\initialize_util.py", line 181, in <lambda>
    shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: sd_models.reload_model_weights()), call=False)
  File "C:\stable-diffusion-webui\modules\sd_models.py", line 977, in reload_model_weights
    load_model(checkpoint_info, already_loaded_state_dict=state_dict)
  File "C:\stable-diffusion-webui\modules\sd_models.py", line 845, in load_model
    load_model_weights(sd_model, checkpoint_info, state_dict, timer)
  File "C:\stable-diffusion-webui\modules\sd_models.py", line 440, in load_model_weights
    model.load_state_dict(state_dict, strict=False)
  File "C:\stable-diffusion-webui\modules\sd_disable_initialization.py", line 223, in <lambda>
    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 "C:\stable-diffusion-webui\modules\sd_disable_initialization.py", line 221, in load_state_dict
    original(module, state_dict, strict=strict)
  File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 2152, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for SD3Inferencer:
        size mismatch for model.diffusion_model.joint_blocks.0.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.0.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.1.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.1.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.2.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.2.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.3.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.3.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.4.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.4.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.5.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.5.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.6.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.6.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.7.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.7.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.8.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.8.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.9.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.9.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.10.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.10.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.11.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.11.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).
        size mismatch for model.diffusion_model.joint_blocks.12.x_block.adaLN_modulation.1.weight: copying a param with shape torch.Size([13824, 1536]) from checkpoint, the shape in current model is torch.Size([9216, 1536]).
        size mismatch for model.diffusion_model.joint_blocks.12.x_block.adaLN_modulation.1.bias: copying a param with shape torch.Size([13824]) from checkpoint, the shape in current model is torch.Size([9216]).

Additional information

The model is SD3.5 medium, T5 text encoder had been disabled +--------------------------------------------------------------------------------------------+ | NVIDIA-SMI 566.03 Driver Version: 566.03 CUDA Version: 12.7 | |-----------------------------------------+------------------------+-------------------------+ | GPU Name Driver-Model | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |========================+==============+===============| | 0 NVIDIA GeForce RTX 4060 WDDM | 00000000:01:00.0 On | v N/A | | 0% 47C P2 N/A / 120W | 6700MiB / 8188MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+------------------------+

TriDefender avatar Nov 01 '24 23:11 TriDefender

i find another issue created that look similiar to your current issue; https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/5070 they have some solutions. i'd like to suggest for you checking here.

linuarM avatar Nov 03 '24 17:11 linuarM

i find another issue created that look similiar to your current issue; #5070 they have some solutions. i'd like to suggest for you checking here.

Didn't work, i think it's because the devs hadn't implemented the new SD3.5 models, i think some one else mentioned it else where, in the stable diffusion's official repository perhaps?

TriDefender avatar Nov 04 '24 11:11 TriDefender

i find another issue created that look similiar to your current issue; #5070 they have some solutions. i'd like to suggest for you checking here.

Didn't work, i think it's because the devs hadn't implemented the new SD3.5 models, i think some one else mentioned it else where, in the stable diffusion's official repository perhaps?

indeed, you are right on point. according from this source sd 3.5 is not supported by stable diffusion yet https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/16590

linuarM avatar Nov 04 '24 11:11 linuarM