adding arguments outside of CLI

[WhoseBoatIsThisBoat]

Hey,

I'm getting an error loading a model and the error message says that the system can recover if I set "ignore_mismatches_sizes"=True
To the question, how do I add custome arguments like that? Is there a file that I can add the argument to or do I need to track down the correct .py-file and add it in there?

So, where do I find the correct message to add this argument?

thanks!

[vladmandic]

you cant, thats not really a user-defined thing.
pls post entire log with error.

[WhoseBoatIsThisBoat]

many thanks for the response!

this is me adding --debug

I load one model successfully, and then fail to load another one:

Using VENV: %ROOT_DIRECTORY%\SD.Next\venv
22:25:40-696030 INFO     Starting SD.Next
22:25:40-698023 INFO     Logger: file="%ROOT_DIRECTORY%\SD.Next\sdnext.log" level=DEBUG size=65 mode=create
22:25:40-699020 INFO     Python: version=3.10.11 platform=Windows bin="%ROOT_DIRECTORY%\SD.Next\venv\Scripts\python.exe"
                         venv="%ROOT_DIRECTORY%\SD.Next\venv"
22:25:40-815581 INFO     Version: app=sd.next updated=2024-11-22 hash=6846f4e5 branch=master
                         url=https://github.com/vladmandic/automatic/tree/master ui=main
22:25:41-066986 INFO     Repository latest available a2f5a39a5919d7edae9b4825a6551c50c854c504 2024-12-09T08:27:14Z
22:25:41-076438 INFO     Platform: arch=AMD64 cpu=Intel64 Family 6 Model 183 Stepping 1, GenuineIntel system=Windows
                         release=Windows-10-10.0.22631-SP0 python=3.10.11 docker=False
22:25:41-077940 DEBUG    Packages: venv=venv site=['venv', 'venv\\lib\\site-packages']
22:25:41-077940 INFO     Args: ['--autolaunch', '--use-cuda', '--debug']
22:25:41-078939 DEBUG    Setting environment tuning
22:25:41-079936 DEBUG    Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
22:25:41-082926 DEBUG    Torch overrides: cuda=True rocm=False ipex=False directml=False openvino=False zluda=False
22:25:41-084923 INFO     CUDA: nVidia toolkit detected
22:25:41-154689 INFO     Install: verifying requirements
22:25:41-158672 INFO     Verifying packages
22:25:41-188467 DEBUG    Timestamp repository update time: Fri Nov 22 13:01:15 2024
22:25:41-189463 INFO     Startup: standard
22:25:41-189463 INFO     Verifying submodules
22:25:44-139289 DEBUG    Git submodule: extensions-builtin/sd-extension-chainner / main
22:25:44-199908 DEBUG    Git submodule: extensions-builtin/sd-extension-system-info / main
22:25:44-251241 DEBUG    Git submodule: extensions-builtin/sd-webui-agent-scheduler / main
22:25:44-326516 DEBUG    Git detached head detected: folder="extensions-builtin/sdnext-modernui" reattach=main
22:25:44-327183 DEBUG    Git submodule: extensions-builtin/sdnext-modernui / main
22:25:44-426201 DEBUG    Git submodule: extensions-builtin/stable-diffusion-webui-rembg / master
22:25:44-480316 DEBUG    Git submodule: modules/k-diffusion / master
22:25:44-553110 DEBUG    Git detached head detected: folder="wiki" reattach=master
22:25:44-553777 DEBUG    Git submodule: wiki / master
22:25:44-603425 DEBUG    Register paths
22:25:44-636754 DEBUG    Installed packages: 198
22:25:44-638088 DEBUG    Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sdnext-modernui', 'stable-diffusion-webui-rembg']
22:25:44-733141 DEBUG    Extension installer:
                         %ROOT_DIRECTORY%\SD.Next\extensions-builtin\sd-webui-agent-scheduler\install.py
22:25:47-672595 DEBUG    Extension installer:
                         %ROOT_DIRECTORY%\SD.Next\extensions-builtin\stable-diffusion-webui-rembg\install.py
22:25:52-624425 INFO     Extension installed packages: stable-diffusion-webui-rembg ['rembg==2.0.61']
22:25:52-629759 DEBUG    Extensions all: ['adetailer']
22:25:52-630426 DEBUG    Extension force: name="adetailer" commit=a89c01d
22:25:52-669107 DEBUG    Extension installer: %ROOT_DIRECTORY%\SD.Next\extensions\adetailer\install.py
22:25:52-799888 INFO     Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sdnext-modernui', 'stable-diffusion-webui-rembg', 'adetailer']
22:25:52-802028 INFO     Install: verifying requirements
22:25:52-803770 DEBUG    Setup complete without errors: 1734924353
22:25:52-806529 DEBUG    Extension preload: {'extensions-builtin': 0.0, 'extensions': 0.0}
22:25:52-807442 INFO     Command line args: ['--autolaunch', '--use-cuda', '--debug'] autolaunch=True use_cuda=True
                         debug=True
22:25:52-808275 DEBUG    Env flags: []
22:25:52-809160 DEBUG    Starting module: <module 'webui' from '%ROOT_DIRECTORY%\\SD.Next\\webui.py'>
22:25:56-226830 INFO     Torch: torch==2.5.1+cu124 torchvision==0.20.1+cu124
22:25:56-227496 INFO     Packages: diffusers==0.32.0.dev0 transformers==4.46.2 accelerate==1.1.1 gradio==3.43.2
22:25:56-625866 DEBUG    Huggingface cache: folder="%USER_DIRECTORY%\.cache\huggingface\hub"
22:25:56-742870 INFO     Device detect: memory=24.0 optimization=none
22:25:56-744204 DEBUG    Read: file="config.json" json=43 bytes=2150 time=0.000
22:25:56-858277 DEBUG    Setting validation: "prompt_attention"="Fixed attention" default="native" choices=['native',
                         'compel', 'xhinker', 'a1111', 'fixed']
22:25:56-859611 WARNING  Setting validation: unknown=['multiple_tqdm']
22:25:56-860944 INFO     Engine: backend=Backend.DIFFUSERS compute=cuda device=cuda attention="Scaled-Dot-Product"
                         mode=no_grad
22:25:56-863611 DEBUG    Read: file="html\reference.json" json=59 bytes=31585 time=0.000
22:25:56-902945 INFO     Torch parameters: backend=cuda device=cuda config=Auto dtype=torch.bfloat16 vae=torch.bfloat16
                         unet=torch.bfloat16 context=no_grad nohalf=False nohalfvae=False upscast=False
                         deterministic=False test-fp16=True test-bf16=True optimization="Scaled-Dot-Product"
22:25:56-992076 DEBUG    ONNX: version=1.20.1 provider=CUDAExecutionProvider, available=['TensorrtExecutionProvider',
                         'CUDAExecutionProvider', 'CPUExecutionProvider']
22:25:57-064415 INFO     Device: device=NVIDIA GeForce RTX 4090 n=1 arch=sm_90 capability=(8, 9) cuda=12.4 cudnn=90100
                         driver=560.94
22:25:57-123082 DEBUG    Importing LDM
22:25:57-130085 DEBUG    Entering start sequence
22:25:57-131418 DEBUG    Initializing
22:25:57-148750 INFO     Available VAEs: path="%ROOT_DIRECTORY%\Models\VAE" items=4
22:25:57-150084 INFO     Available UNets: path="%ROOT_DIRECTORY%\Models\UNET" items=4
22:25:57-150751 INFO     Available TEs: path="%ROOT_DIRECTORY%\Models\Text-encoder" items=0
22:25:57-152084 INFO     Disabled extensions: ['sdnext-modernui']
22:25:57-153419 DEBUG    Read: file="cache.json" json=2 bytes=17244 time=0.000
22:25:57-163418 DEBUG    Read: file="metadata.json" json=408 bytes=7312037 time=0.008
22:25:57-166084 DEBUG    Scanning diffusers cache: folder="%ROOT_DIRECTORY%\Models\Diffusers" items=1 time=0.00
22:25:57-167418 INFO     Available Models: path="%ROOT_DIRECTORY%\Models\Stable-diffusion" items=33 time=0.01
22:25:57-204751 INFO     Available Yolo: path="%ROOT_DIRECTORY%\Models\yolo" items=7 downloaded=2
22:25:57-206084 INFO     Load extensions
22:25:57-364154 INFO     Available LoRAs: path="%ROOT_DIRECTORY%\Models\Lora" items=197 folders=2 time=0.01
22:25:57-728198 INFO     Extension: script='extensions-builtin\sd-webui-agent-scheduler\scripts\task_scheduler.py' Using
                         sqlite file: extensions-builtin\sd-webui-agent-scheduler\task_scheduler.sqlite3
22:25:57-843785 INFO     Extension: script='extensions\adetailer\scripts\!adetailer.py' [-] ADetailer initialized.
                         version: 24.5.1, num models: 12
22:25:57-844782 DEBUG    Extensions init time: 0.64 pulid_ext.py=0.10 Lora=0.13 sd-webui-agent-scheduler=0.23
                         adetailer=0.11
22:25:57-853752 DEBUG    Read: file="html/upscalers.json" json=4 bytes=2672 time=0.000
22:25:57-854748 DEBUG    Read: file="extensions-builtin\sd-extension-chainner\models.json" json=24 bytes=2719 time=0.000
22:25:57-855745 DEBUG    chaiNNer models: path="%ROOT_DIRECTORY%\Models\chaiNNer" defined=24 discovered=0 downloaded=0
22:25:57-856741 DEBUG    Upscaler type=ESRGAN folder="%ROOT_DIRECTORY%\Models\ESRGAN"
                         model="1x-ITF-SkinDiffDetail-Lite-v1"
                         path="%ROOT_DIRECTORY%\Models\ESRGAN\1x-ITF-SkinDiffDetail-Lite-v1.pth"
22:25:57-858731 INFO     Available Upscalers: items=54 downloaded=8 user=1 time=0.01 types=['None', 'Lanczos',
                         'Nearest', 'ChaiNNer', 'AuraSR', 'ESRGAN', 'LDSR', 'RealESRGAN', 'SCUNet', 'SD', 'SwinIR']
22:25:57-866705 INFO     Available Styles: folder="%ROOT_DIRECTORY%\Models\styles" items=288 time=0.01
22:25:57-870420 INFO     UI start
22:25:57-871425 DEBUG    UI themes available: type=Standard themes=12
22:25:57-872373 INFO     UI theme: type=Standard name="black-teal"
22:25:57-875363 DEBUG    UI theme: css="%ROOT_DIRECTORY%\SD.Next\javascript\black-teal.css" base="sdnext.css" user="None"
22:25:57-877356 DEBUG    UI initialize: txt2img
22:25:58-013019 DEBUG    Networks: page='model' items=91 subfolders=2 tab=txt2img
                         folders=['%ROOT_DIRECTORY%\\Models\\Stable-diffusion', '%ROOT_DIRECTORY%\\Models\\Diffusers',
                         'models\\Reference'] list=0.11 thumb=0.03 desc=0.02 info=0.06 workers=8 sort=Name [A-Z]
22:25:58-017736 DEBUG    Networks: page='lora' items=197 subfolders=0 tab=txt2img
                         folders=['%ROOT_DIRECTORY%\\Models\\Lora', '%ROOT_DIRECTORY%\\Models\\LyCORIS'] list=0.12
                         thumb=0.01 desc=0.09 info=0.30 workers=8 sort=Name [A-Z]
22:25:58-025102 DEBUG    Networks: page='style' items=288 subfolders=1 tab=txt2img
                         folders=['%ROOT_DIRECTORY%\\Models\\styles', 'html'] list=0.10 thumb=0.00 desc=0.00 info=0.00
                         workers=8 sort=Name [A-Z]
22:25:58-029597 DEBUG    Networks: page='embedding' items=23 subfolders=0 tab=txt2img
                         folders=['%ROOT_DIRECTORY%\\Models\\embeddings'] list=0.09 thumb=0.02 desc=0.01 info=0.02
                         workers=8 sort=Name [A-Z]
22:25:58-033584 DEBUG    Networks: page='vae' items=4 subfolders=0 tab=txt2img folders=['%ROOT_DIRECTORY%\\Models\\VAE']
                         list=0.05 thumb=0.04 desc=0.00 info=0.01 workers=8 sort=Name [A-Z]
22:25:58-035577 DEBUG    Networks: page='history' items=0 subfolders=0 tab=txt2img folders=[] list=0.00 thumb=0.00
                         desc=0.00 info=0.00 workers=8 sort=Name [A-Z]
22:25:58-244816 DEBUG    UI initialize: img2img
22:25:58-399570 DEBUG    UI initialize: control models=%ROOT_DIRECTORY%\Models\control
22:25:58-697840 DEBUG    Read: file="ui-config.json" json=0 bytes=2 time=0.000
22:25:58-802167 DEBUG    UI themes available: type=Standard themes=12
22:25:59-717263 DEBUG    Extension list: processed=393 installed=7 enabled=6 disabled=1 visible=393 hidden=0
22:25:59-822124 DEBUG    Root paths: ['%ROOT_DIRECTORY%\\SD.Next']
22:25:59-887136 INFO     Local URL: http://127.0.0.1:7860/
22:25:59-887819 DEBUG    Gradio functions: registered=2200
22:25:59-889186 DEBUG    API middleware: [<class 'starlette.middleware.base.BaseHTTPMiddleware'>, <class
                         'starlette.middleware.gzip.GZipMiddleware'>]
22:25:59-891919 DEBUG    API initialize
22:26:00-016263 INFO     [AgentScheduler] Task queue is empty
22:26:00-017174 INFO     [AgentScheduler] Registering APIs
22:26:00-259864 DEBUG    Scripts setup: ['IP Adapters:0.023', 'ADetailer:0.068', 'XYZ Grid:0.032', 'Ctrl-X: Controlling
                         Structure and Appearance:0.006', 'Face: Multiple ID Transfers:0.015', 'K-Diffusion
                         Samplers:0.084', 'LUT Color grading:0.006', 'PuLID: ID Customization:0.006', 'Video
                         AnimateDiff:0.007', 'Video CogVideoX:0.009', 'Video VGen Image-to-Video:0.007']
22:26:00-261560 DEBUG    Model metadata: file="metadata.json" no changes
22:26:00-262244 DEBUG    Model auto load disabled
22:26:00-264294 DEBUG    Script callback init time: task_scheduler.py:app_started=0.26
22:26:00-265661 DEBUG    Save: file="config.json" json=43 bytes=2089 time=0.002
22:26:00-267027 INFO     Startup time: 7.45 torch=2.67 gradio=0.58 diffusers=0.06 libraries=0.98 extensions=0.64
                         ui-networks=0.27 ui-txt2img=0.19 ui-img2img=0.12 ui-control=0.16 ui-settings=0.33
                         ui-extensions=0.71 ui-defaults=0.06 launch=0.11 api=0.07 app-started=0.30
22:26:00-268394 DEBUG    Settings: unused=['multiple_tqdm']
22:26:00-270444 INFO     Launching browser
22:26:00-303346 DEBUG    Server: alive=True requests=1 memory=1.02/63.75 status='idle' task='' timestamp=None id=''
                         job=0 jobs=0 total=0 step=0 steps=0 queued=0 uptime=4 elapsed=None eta=None progress=0
22:26:02-676508 INFO     MOTD: N/A
22:26:06-961197 DEBUG    UI themes available: type=Standard themes=12
22:26:07-300974 INFO     Browser session: user=None client=127.0.0.1 agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64)
                         AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36
22:28:00-272650 DEBUG    Server: alive=True requests=65 memory=1.03/63.75 status='idle' task='' timestamp=None id=''
                         job=0 jobs=0 total=0 step=0 steps=0 queued=0 uptime=124 elapsed=None eta=None progress=0
22:30:00-131059 DEBUG    Server: alive=True requests=67 memory=1.03/63.75 status='idle' task='' timestamp=None id=''
                         job=0 jobs=0 total=0 step=0 steps=0 queued=0 uptime=244 elapsed=None eta=None progress=0
22:32:00-240844 DEBUG    Server: alive=True requests=70 memory=1.03/63.75 status='idle' task='' timestamp=None id=''
                         job=0 jobs=0 total=0 step=0 steps=0 queued=0 uptime=364 elapsed=None eta=None progress=0
22:32:06-474754 DEBUG    Scanning diffusers cache: folder="%ROOT_DIRECTORY%\Models\Diffusers" items=1 time=0.00
22:32:06-477743 INFO     Available Models: path="%ROOT_DIRECTORY%\Models\Stable-diffusion" items=33 time=0.01
22:32:12-966621 INFO     Load model: select="PONY, ChrismixPNY-NSFW v2.0 [03335fed37]"
22:32:12-970608 INFO     Autodetect model: detect="Stable Diffusion XL" class=StableDiffusionXLPipeline
                         file="%ROOT_DIRECTORY%\Models\Stable-diffusion\PONY, ChrismixPNY-NSFW v2.0.safetensors"
                         size=6776MB
22:32:12-989544 DEBUG    Autodetect: modules={'conditioner': {'embedders': {}}, 'first_stage_model': {'decoder': {},
                         'encoder': {}, 'post_quant_conv': {}, 'quant_conv': {}}, 'model': {'diffusion_model': {}}}
                         list=['conditioner.embedders', 'first_stage_model.decoder', 'first_stage_model.encoder',
                         'first_stage_model.post_quant_conv', 'first_stage_model.quant_conv', 'model.diffusion_model']
                         time=0.02
22:32:12-991541 INFO     Autodetect vae: detect="Stable Diffusion XL" class=StableDiffusionXLPipeline
                         file="%ROOT_DIRECTORY%\Models\Stable-diffusion\PONY, ChrismixPNY-NSFW v2.0.safetensors"
                         size=6776MB
22:32:13-000507 DEBUG    Autodetect: modules={'conditioner': {'embedders': {}}, 'first_stage_model': {'decoder': {},
                         'encoder': {}, 'post_quant_conv': {}, 'quant_conv': {}}, 'model': {'diffusion_model': {}}}
                         list=['conditioner.embedders', 'first_stage_model.decoder', 'first_stage_model.encoder',
                         'first_stage_model.post_quant_conv', 'first_stage_model.quant_conv', 'model.diffusion_model']
                         time=0.01
22:32:13-002501 INFO     Load module: type=VAE model="%ROOT_DIRECTORY%\Models\VAE\sdxl_vae.safetensors" source=settings
                         config={'low_cpu_mem_usage': False, 'torch_dtype': torch.bfloat16, 'use_safetensors': True,
                         'config': 'configs/sdxl\\vae'}
Diffusers  5.65s/it ████████ 100% 7/7 00:39 00:00 Loading pipeline components...
22:32:55-474386 DEBUG    Setting model: pipeline=StableDiffusionXLPipeline config={'low_cpu_mem_usage': True,
                         'torch_dtype': torch.bfloat16, 'load_connected_pipeline': True, 'extract_ema': False, 'config':
                         'configs/sdxl', 'use_safetensors': True, 'cache_dir':
                         '%USER_DIRECTORY%\\.cache\\huggingface\\hub'}
22:33:00-445658 INFO     Load network: type=embeddings loaded=10 skipped=13 time=4.97
22:33:00-447406 DEBUG    Setting model: component=VAE name="sdxl_vae.safetensors"
22:33:00-448691 DEBUG    Setting model: component=VAE slicing=True
22:33:00-448691 DEBUG    Setting model: component=VAE tiling=True
22:33:00-449681 DEBUG    Setting model: attention="Scaled-Dot-Product"
22:33:00-469617 DEBUG    Setting model: offload=none
22:33:00-471609 DEBUG    Read: file="%ROOT_DIRECTORY%\SD.Next\configs\sdxl\vae\config.json" json=15 bytes=674 time=0.000
22:33:01-671534 DEBUG    Model move: device=cuda class=StableDiffusionXLPipeline accelerate=False
                         fn=reload_model_weights:load_diffuser time=1.20
22:33:01-861565 DEBUG    GC: utilization={'gpu': 35, 'ram': 11, 'threshold': 80} gc={'collected': 3234, 'saved': 0.0}
                         before={'gpu': 8.38, 'ram': 7.24} after={'gpu': 8.38, 'ram': 7.24, 'retries': 0, 'oom': 0}
                         device=cuda fn=reload_model_weights:load_diffuser time=0.19
22:33:01-868541 INFO     Load model: time=48.70 vae=2.22 load=40.29 embeddings=4.97 move=1.20 native=1024 memory={'ram':
                         {'used': 7.24, 'total': 63.75}, 'gpu': {'used': 8.38, 'total': 23.99}, 'retries': 0, 'oom': 0}
22:33:01-870535 DEBUG    Setting changed: sd_model_checkpoint=PONY, ChrismixPNY-NSFW v2.0 [03335fed37] progress=True
22:33:01-871532 DEBUG    Save: file="config.json" json=43 bytes=2105 time=0.001
22:33:01-874521 DEBUG    Settings: unused=['multiple_tqdm']
22:33:12-793715 INFO     Load model: select="PONY, Chrismix NSFW v3.0"
22:33:15-636755 DEBUG    Model move: device=cpu class=StableDiffusionXLPipeline accelerate=False
                         fn=<lambda>:reload_model_weights time=2.84
22:33:16-052962 DEBUG    GC: utilization={'gpu': 35, 'ram': 12, 'threshold': 80} gc={'collected': 621, 'saved': 6.78}
                         before={'gpu': 8.38, 'ram': 7.62} after={'gpu': 1.6, 'ram': 7.62, 'retries': 0, 'oom': 0}
                         device=cuda fn=reload_model_weights:unload_model_weights time=0.36
22:33:16-054956 DEBUG    Unload weights model: {'ram': {'used': 7.62, 'total': 63.75}, 'gpu': {'used': 1.6, 'total':
                         23.99}, 'retries': 0, 'oom': 0}
22:33:16-069907 INFO     Autodetect model: detect="Stable Diffusion" class=StableDiffusionPipeline
                         file="%ROOT_DIRECTORY%\Models\Stable-diffusion\PONY, Chrismix NSFW v3.0.safetensors" size=13233MB
22:33:16-085532 DEBUG    Autodetect: modules={'conditioner': {'embedders': {}}, 'first_stage_model': {'decoder': {},
                         'encoder': {}, 'post_quant_conv': {}, 'quant_conv': {}}, 'model': {'diffusion_model': {}}}
                         list=['conditioner.embedders', 'first_stage_model.decoder', 'first_stage_model.encoder',
                         'first_stage_model.post_quant_conv', 'first_stage_model.quant_conv', 'model.diffusion_model']
                         time=0.01
22:33:16-087525 INFO     Autodetect vae: detect="Stable Diffusion" class=StableDiffusionPipeline
                         file="%ROOT_DIRECTORY%\Models\Stable-diffusion\PONY, Chrismix NSFW v3.0.safetensors" size=13233MB
22:33:16-106954 DEBUG    Autodetect: modules={'conditioner': {'embedders': {}}, 'first_stage_model': {'decoder': {},
                         'encoder': {}, 'post_quant_conv': {}, 'quant_conv': {}}, 'model': {'diffusion_model': {}}}
                         list=['conditioner.embedders', 'first_stage_model.decoder', 'first_stage_model.encoder',
                         'first_stage_model.post_quant_conv', 'first_stage_model.quant_conv', 'model.diffusion_model']
                         time=0.02
22:33:16-112931 INFO     Load module: type=VAE model="%ROOT_DIRECTORY%\Models\VAE\sdxl_vae.safetensors" source=settings
                         config={'low_cpu_mem_usage': False, 'torch_dtype': torch.bfloat16, 'use_safetensors': True,
                         'config': 'configs/sd15\\vae'}
Diffusers  1.14it/s █████▎    67% 4/6 00:03 00:01 Loading pipeline components...
22:33:20-347678 ERROR    Load model: file="%ROOT_DIRECTORY%\Models\Stable-diffusion\PONY, Chrismix NSFW v3.0.safetensors"
                         pipeline=Autodetect/NoneType config={'low_cpu_mem_usage': True, 'torch_dtype': torch.bfloat16,
                         'load_connected_pipeline': True, 'safety_checker': None, 'requires_safety_checker': False,
                         'vae': AutoencoderKL(
                           (encoder): Encoder(
                             (conv_in): Conv2d(3, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                             (down_blocks): ModuleList(
                               (0): DownEncoderBlock2D(
                                 (resnets): ModuleList(
                                   (0-1): 2 x ResnetBlock2D(
                                     (norm1): GroupNorm(32, 128, eps=1e-06, affine=True)
                                     (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 128, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                   )
                                 )
                                 (downsamplers): ModuleList(
                                   (0): Downsample2D(
                                     (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2))
                                   )
                                 )
                               )
                               (1): DownEncoderBlock2D(
                                 (resnets): ModuleList(
                                   (0): ResnetBlock2D(
                                     (norm1): GroupNorm(32, 128, eps=1e-06, affine=True)
                                     (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 256, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                     (conv_shortcut): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1))
                                   )
                                   (1): ResnetBlock2D(
                                     (norm1): GroupNorm(32, 256, eps=1e-06, affine=True)
                                     (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 256, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                   )
                                 )
                                 (downsamplers): ModuleList(
                                   (0): Downsample2D(
                                     (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2))
                                   )
                                 )
                               )
                               (2): DownEncoderBlock2D(
                                 (resnets): ModuleList(
                                   (0): ResnetBlock2D(
                                     (norm1): GroupNorm(32, 256, eps=1e-06, affine=True)
                                     (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                     (conv_shortcut): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1))
                                   )
                                   (1): ResnetBlock2D(
                                     (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
                                     (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                   )
                                 )
                                 (downsamplers): ModuleList(
                                   (0): Downsample2D(
                                     (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2))
                                   )
                                 )
                               )
                               (3): DownEncoderBlock2D(
                                 (resnets): ModuleList(
                                   (0-1): 2 x ResnetBlock2D(
                                     (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
                                     (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                   )
                                 )
                               )
                             )
                             (mid_block): UNetMidBlock2D(
                               (attentions): ModuleList(
                                 (0): Attention(
                                   (group_norm): GroupNorm(32, 512, eps=1e-06, affine=True)
                                   (to_q): Linear(in_features=512, out_features=512, bias=True)
                                   (to_k): Linear(in_features=512, out_features=512, bias=True)
                                   (to_v): Linear(in_features=512, out_features=512, bias=True)
                                   (to_out): ModuleList(
                                     (0): Linear(in_features=512, out_features=512, bias=True)
                                     (1): Dropout(p=0.0, inplace=False)
                                   )
                                 )
                               )
                               (resnets): ModuleList(
                                 (0-1): 2 x ResnetBlock2D(
                                   (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
                                   (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                   (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
                                   (dropout): Dropout(p=0.0, inplace=False)
                                   (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                   (nonlinearity): SiLU()
                                 )
                               )
                             )
                             (conv_norm_out): GroupNorm(32, 512, eps=1e-06, affine=True)
                             (conv_act): SiLU()
                             (conv_out): Conv2d(512, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                           )
                           (decoder): Decoder(
                             (conv_in): Conv2d(4, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                             (up_blocks): ModuleList(
                               (0-1): 2 x UpDecoderBlock2D(
                                 (resnets): ModuleList(
                                   (0-2): 3 x ResnetBlock2D(
                                     (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
                                     (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                   )
                                 )
                                 (upsamplers): ModuleList(
                                   (0): Upsample2D(
                                     (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                   )
                                 )
                               )
                               (2): UpDecoderBlock2D(
                                 (resnets): ModuleList(
                                   (0): ResnetBlock2D(
                                     (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
                                     (conv1): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 256, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                     (conv_shortcut): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
                                   )
                                   (1-2): 2 x ResnetBlock2D(
                                     (norm1): GroupNorm(32, 256, eps=1e-06, affine=True)
                                     (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 256, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                   )
                                 )
                                 (upsamplers): ModuleList(
                                   (0): Upsample2D(
                                     (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                   )
                                 )
                               )
                               (3): UpDecoderBlock2D(
                                 (resnets): ModuleList(
                                   (0): ResnetBlock2D(
                                     (norm1): GroupNorm(32, 256, eps=1e-06, affine=True)
                                     (conv1): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 128, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                     (conv_shortcut): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
                                   )
                                   (1-2): 2 x ResnetBlock2D(
                                     (norm1): GroupNorm(32, 128, eps=1e-06, affine=True)
                                     (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (norm2): GroupNorm(32, 128, eps=1e-06, affine=True)
                                     (dropout): Dropout(p=0.0, inplace=False)
                                     (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                     (nonlinearity): SiLU()
                                   )
                                 )
                               )
                             )
                             (mid_block): UNetMidBlock2D(
                               (attentions): ModuleList(
                                 (0): Attention(
                                   (group_norm): GroupNorm(32, 512, eps=1e-06, affine=True)
                                   (to_q): Linear(in_features=512, out_features=512, bias=True)
                                   (to_k): Linear(in_features=512, out_features=512, bias=True)
                                   (to_v): Linear(in_features=512, out_features=512, bias=True)
                                   (to_out): ModuleList(
                                     (0): Linear(in_features=512, out_features=512, bias=True)
                                     (1): Dropout(p=0.0, inplace=False)
                                   )
                                 )
                               )
                               (resnets): ModuleList(
                                 (0-1): 2 x ResnetBlock2D(
                                   (norm1): GroupNorm(32, 512, eps=1e-06, affine=True)
                                   (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                   (norm2): GroupNorm(32, 512, eps=1e-06, affine=True)
                                   (dropout): Dropout(p=0.0, inplace=False)
                                   (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                                   (nonlinearity): SiLU()
                                 )
                               )
                             )
                             (conv_norm_out): GroupNorm(32, 128, eps=1e-06, affine=True)
                             (conv_act): SiLU()
                             (conv_out): Conv2d(128, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
                           )
                           (quant_conv): Conv2d(8, 8, kernel_size=(1, 1), stride=(1, 1))
                           (post_quant_conv): Conv2d(4, 4, kernel_size=(1, 1), stride=(1, 1))
                         ), 'local_files_only': False, 'extract_ema': False, 'config': 'configs/sd15',
                         'use_safetensors': True, 'cache_dir': '%USER_DIRECTORY%\\.cache\\huggingface\\hub'} Cannot load
                         because down_blocks.1.attentions.0.proj_in.weight expected shape tensor(..., device='meta',
                         size=(640, 640, 1, 1)), but got torch.Size([640, 640]). If you want to instead overwrite
                         randomly initialized weights, please make sure to pass both `low_cpu_mem_usage=False` and
                         `ignore_mismatched_sizes=True`. For more information, see also:
                         https://github.com/huggingface/diffusers/issues/1619#issuecomment-1345604389 as an example.
22:33:20-395497 ERROR    Load: ValueError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ %ROOT_DIRECTORY%\SD.Next\modules\sd_models.py:745 in load_diffuser_file                                                │
│                                                                                                                      │
│    744 │   │   │   │   sd_hijack_accelerate.restore_accelerate()                                                     │
│ ❱  745 │   │   │   sd_model = pipeline.from_single_file(checkpoint_info.path, **diffusers_load_config)               │
│    746 │   │   │   # sd_model = patch_diffuser_config(sd_model, checkpoint_info.path)                                │
│                                                                                                                      │
│ %ROOT_DIRECTORY%\SD.Next\venv\lib\site-packages\huggingface_hub\utils\_validators.py:114 in _inner_fn                  │
│                                                                                                                      │
│   113 │   │                                                                                                          │
│ ❱ 114 │   │   return fn(*args, **kwargs)                                                                             │
│   115                                                                                                                │
│                                                                                                                      │
│ %ROOT_DIRECTORY%\SD.Next\venv\lib\site-packages\diffusers\loaders\single_file.py:495 in from_single_file               │
│                                                                                                                      │
│   494 │   │   │   │   try:                                                                                           │
│ ❱ 495 │   │   │   │   │   loaded_sub_model = load_single_file_sub_model(                                             │
│   496 │   │   │   │   │   │   library_name=library_name,                                                             │
│                                                                                                                      │
│ %ROOT_DIRECTORY%\SD.Next\venv\lib\site-packages\diffusers\loaders\single_file.py:102 in load_single_file_sub_model     │
│                                                                                                                      │
│   101 │   │                                                                                                          │
│ ❱ 102 │   │   loaded_sub_model = load_method(                                                                        │
│   103 │   │   │   pretrained_model_link_or_path_or_dict=checkpoint,                                                  │
│                                                                                                                      │
│ %ROOT_DIRECTORY%\SD.Next\venv\lib\site-packages\huggingface_hub\utils\_validators.py:114 in _inner_fn                  │
│                                                                                                                      │
│   113 │   │                                                                                                          │
│ ❱ 114 │   │   return fn(*args, **kwargs)                                                                             │
│   115                                                                                                                │
│                                                                                                                      │
│ %ROOT_DIRECTORY%\SD.Next\venv\lib\site-packages\diffusers\loaders\single_file_model.py:299 in from_single_file         │
│                                                                                                                      │
│   298 │   │   if is_accelerate_available():                                                                          │
│ ❱ 299 │   │   │   unexpected_keys = load_model_dict_into_meta(model, diffusers_format_checkpoint, dtype=torch_dtype) │
│   300                                                                                                                │
│                                                                                                                      │
│ %ROOT_DIRECTORY%\SD.Next\venv\lib\site-packages\diffusers\models\model_loading_utils.py:223 in load_model_dict_into_me │
│                                                                                                                      │
│   222 │   │   │   │   model_name_or_path_str = f"{model_name_or_path} " if model_name_or_path is not None else ""    │
│ ❱ 223 │   │   │   │   raise ValueError(                                                                              │
│   224 │   │   │   │   │   f"Cannot load {model_name_or_path_str} because {param_name} expected shape {empty_state_di │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
ValueError: Cannot load  because down_blocks.1.attentions.0.proj_in.weight expected shape tensor(..., device='meta', size=(640, 640, 1, 1)), but got torch.Size([640, 640]). If you want to instead overwrite randomly initialized weights, please make sure to pass both `low_cpu_mem_usage=False` and `ignore_mismatched_sizes=True`. For more information, see also: https://github.com/huggingface/diffusers/issues/1619#issuecomment-1345604389 as an example.
22:33:20-642708 ERROR    Load model: name="PONY, Chrismix NSFW v3.0" not loaded
22:33:20-645700 DEBUG    Setting changed: sd_model_checkpoint=PONY, Chrismix NSFW v3.0 progress=True
22:33:20-648689 DEBUG    Save: file="config.json" json=43 bytes=2089 time=0.004
22:33:20-649686 DEBUG    Settings: unused=['multiple_tqdm']

[vladmandic]

loading first model:

22:32:12-966621 INFO     Load model: select="PONY, ChrismixPNY-NSFW v2.0 [03335fed37]"
22:32:12-970608 INFO     Autodetect model: detect="Stable Diffusion XL" class=StableDiffusionXLPipeline

loading second model:

22:33:12-793715 INFO     Load model: select="PONY, Chrismix NSFW v3.0"
22:33:16-069907 INFO     Autodetect model: detect="Stable Diffusion" class=StableDiffusionPipeline
                         file="%ROOT_DIRECTORY%\Models\Stable-diffusion\PONY, Chrismix NSFW v3.0.safetensors" size=13233MB
22:33:20-347678 ERROR    Load model: file="%ROOT_DIRECTORY%\Models\Stable-diffusion\PONY, Chrismix NSFW v3.0.safetensors"
                         pipeline=Autodetect/NoneType config={'low_cpu_mem_usage': True, 'torch_dtype': torch.bfloat16,

that second model has a weird size and its not autodetected as XL model, so loading failed.
you can force pipiline type in settings to SDXL instead of autodetect.
i dont know why autodetect fails, but any SDXL model that is 13gb in size is not worth paying attention to in my book, that's just bloatware.

[WhoseBoatIsThisBoat]

Thanks for the reply!

How do I force SD.Next to load it as an SDXL model?

[vladmandic]

in settings - select pipine type instead of auto detect.

[WhoseBoatIsThisBoat]

that worked

cheers!