automatic
automatic copied to clipboard
vladmandic
[Issue]: Failure to load a video component loads base diffusion model
Issue Description
When loading any component for a video model in the video tab fails, SDNext immediately starts loading whatever model is present in the Base model selector.
For example, in the log below (the exact loading error itself is irrelevant for this issue, it happens no matter what the error is, such as download errors) after a failed attempt to load the transformers for Wan2.2 14B it immediately loads in the SDXL model I happened to have selected in the menu, turning the log into a mess, and forcing a weird state where futher video attempts are unsuccesfull, only resolved by restart:
02:43:04-995916 DEBUG Video: cls=StableDiffusionXLPipeline width=800 height=992 frames=17 steps=20
02:43:04-997416 INFO Applying HyperTile: unet=128/384
02:43:05-051754 ERROR Mismatch: type=sdxl cls=StableDiffusionXLPipeline request=StableDiffusionProcessingVideo
non-video model with video pipeline
Version Platform Description
02:23:26-567441 INFO Python: version=3.12.10 platform=Windows bin="E:\AI-ImageGen\sdnext_dev\venv\Scripts\python.exe" venv="E:\AI-ImageGen\sdnext_dev\venv" 02:23:26-833939 INFO Version: app=sd.next updated=2025-08-17 hash=85d494ee branch=dev url=https://github.com/vladmandic/sdnext.git/tree/dev ui=dev 02:23:27-684256 INFO Version: app=sd.next latest=2025-08-17T02:19:44Z hash=85d494ee branch=dev 02:23:27-724760 INFO Platform: arch=AMD64 cpu=Intel64 Family 6 Model 158 Stepping 12, GenuineIntel system=Windows release=Windows-11-10.0.26100-SP0 python=3.12.10 locale=('English_United Kingdom', '1252') docker=False
Relevant log output
02:23:26-561940 INFO Starting SD.Next
02:23:26-565938 INFO Logger: file="E:\AI-ImageGen\sdnext_dev\sdnext.log" level=DEBUG host="TennesseeDesk" size=81
mode=create
02:23:26-567441 INFO Python: version=3.12.10 platform=Windows
bin="E:\AI-ImageGen\sdnext_dev\venv\Scripts\python.exe" venv="E:\AI-ImageGen\sdnext_dev\venv"
02:23:26-833939 INFO Version: app=sd.next updated=2025-08-17 hash=85d494ee branch=dev
url=https://github.com/vladmandic/sdnext.git/tree/dev ui=dev
02:23:27-684256 INFO Version: app=sd.next latest=2025-08-17T02:19:44Z hash=85d494ee branch=dev
02:23:27-724760 INFO Platform: arch=AMD64 cpu=Intel64 Family 6 Model 158 Stepping 12, GenuineIntel system=Windows
release=Windows-11-10.0.26100-SP0 python=3.12.10 locale=('English_United Kingdom', '1252')
docker=False
02:23:27-726260 DEBUG Packages: prefix=venv site=['venv', 'venv\\Lib\\site-packages']
02:23:27-727757 INFO Args: ['--port', '7855', '--uv', '--insecure', '--debug', '--update']
02:23:27-728757 DEBUG Setting environment tuning
02:23:27-729757 DEBUG Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
02:23:27-731260 INFO Verifying torch installation
02:23:27-747755 DEBUG Torch overrides: cuda=False rocm=False ipex=False directml=False openvino=False zluda=False
02:23:27-781757 INFO CUDA: nVidia toolkit detected
02:23:27-947163 INFO Install: verifying requirements
02:23:27-951138 INFO Startup: standard
02:23:27-952170 INFO Verifying submodules
02:23:30-706495 DEBUG Git submodule: extensions-builtin/sd-extension-chainner / main
02:23:31-797586 DEBUG Git submodule: extensions-builtin/sd-extension-system-info / main
02:23:32-805120 DEBUG Git submodule: extensions-builtin/sd-webui-agent-scheduler / main
02:23:33-868907 DEBUG Git submodule: extensions-builtin/sdnext-modernui / dev
02:23:34-924260 DEBUG Git submodule: extensions-builtin/stable-diffusion-webui-rembg / master
02:23:35-993911 DEBUG Git submodule: wiki / master
02:23:37-084652 DEBUG Installed packages: 185
02:23:37-086182 DEBUG Extensions all: ['sd-extension-chainner', 'sd-extension-system-info',
'sd-webui-agent-scheduler', 'sdnext-modernui', 'stable-diffusion-webui-rembg']
02:23:37-176651 DEBUG Git submodule: extensions-builtin\sd-extension-chainner / main
02:23:38-291967 DEBUG Git submodule: extensions-builtin\sd-extension-system-info / main
02:23:39-409273 DEBUG Git submodule: extensions-builtin\sd-webui-agent-scheduler / main
02:23:40-374402 DEBUG Extension installer: builtin=True
file="E:\AI-ImageGen\sdnext_dev\extensions-builtin\sd-webui-agent-scheduler\install.py"
02:23:40-542114 DEBUG Git submodule: extensions-builtin\sdnext-modernui / dev
02:23:41-653782 DEBUG Git submodule: extensions-builtin\stable-diffusion-webui-rembg / master
02:23:42-671664 DEBUG Extension installer: builtin=True
file="E:\AI-ImageGen\sdnext_dev\extensions-builtin\stable-diffusion-webui-rembg\install.py"
02:23:42-745704 DEBUG Extensions all: ['OneButtonPrompt', 'sd-dynamic-prompts']
02:23:42-836409 DEBUG Git submodule: extensions\OneButtonPrompt / main
02:23:43-919192 DEBUG Git submodule: extensions\sd-dynamic-prompts / main
02:23:44-914501 DEBUG Extension installer: builtin=False
file="E:\AI-ImageGen\sdnext_dev\extensions\sd-dynamic-prompts\install.py"
02:23:45-192287 INFO Extensions enabled: ['sd-extension-chainner', 'sd-extension-system-info',
'sd-webui-agent-scheduler', 'sdnext-modernui', 'stable-diffusion-webui-rembg',
'OneButtonPrompt', 'sd-dynamic-prompts']
02:23:45-266318 INFO Install: verifying requirements
02:23:45-270789 INFO Updating Wiki
02:23:45-362299 DEBUG Git submodule: E:\AI-ImageGen\sdnext_dev\wiki / master
02:23:46-318813 DEBUG Setup complete without errors: 1755480226
02:23:46-323836 DEBUG Extension preload: {'extensions-builtin': 0.0, 'extensions': 0.0}
02:23:46-325337 INFO Installer time: total=54.29 git=17.62 update=14.85 submodules=9.06 branch=1.41
sd-dynamic-prompts=1.36 stable-diffusion-webui-rembg=1.18 sd-webui-agent-scheduler=1.13
sd-extension-system-info=1.12 sd-extension-chainner=1.12 latest=1.11 sdnext-modernui=1.11
OneButtonPrompt=1.08 wiki=1.05 base=0.34 version=0.26 installed=0.15 requirements=0.15
files=0.09 torch=0.05
02:23:46-327339 INFO Command line args: ['--port', '7855', '--uv', '--insecure', '--debug', '--update']
insecure=True port=7855 upgrade=True uv=True debug=True args=[]
02:23:46-328812 DEBUG Env flags: []
02:23:46-329313 DEBUG Starting module: <module 'webui' from 'E:\\AI-ImageGen\\sdnext_dev\\webui.py'>
Multiple distributions found for package optimum. Picked distribution: optimum
02:23:56-349984 INFO Torch: torch==2.7.1+cu128 torchvision==0.22.1+cu128
02:23:56-352955 INFO Packages: diffusers==0.35.0.dev0 transformers==4.55.2 accelerate==1.10.0 gradio==3.43.2
pydantic==1.10.21 numpy==2.1.2
02:23:56-868382 DEBUG ONNX: version=1.22.1, available=['AzureExecutionProvider', 'CPUExecutionProvider']
02:23:57-025455 DEBUG State initialized: id=2233658267632
02:23:57-109457 INFO Device detect: memory=24.0 default=balanced optimization=highvram
02:23:57-114481 DEBUG Read: file="E:\AI-ImageGen\sdnext_dev\config.json" json=42 bytes=2528 time=0.000
fn=<module>:load
02:23:57-116489 DEBUG Setting validation: "schedulers_sigma"="betas" default="default" choices=['default', 'karras',
'exponential', 'polyexponential']
02:23:57-117491 DEBUG Setting validation: "schedulers_beta_schedule"="scaled" default="default" choices=['default',
'linear', 'scaled_linear', 'squaredcos_cap_v2', 'sigmoid']
02:23:57-119514 INFO Engine: backend=Backend.DIFFUSERS compute=cuda device=cuda attention="Scaled-Dot-Product"
mode=no_grad
02:23:57-120490 DEBUG Torch cuDNN: benchmark=True
02:23:57-121514 DEBUG Torch attention: type="sdpa" flash=True memory=True math=True
02:23:57-123498 DEBUG Torch attention: type="dynamic attention"
02:23:57-181067 INFO Torch parameters: backend=cuda device=cuda config=Auto dtype=torch.bfloat16 context=no_grad
nohalf=False nohalfvae=False upcast=False deterministic=False tunable=[False, True] fp16=pass
bf16=pass optimization="Scaled-Dot-Product"
02:23:57-258535 INFO Device: device=NVIDIA GeForce RTX 3090 n=1 arch=sm_120 capability=(8, 6) cuda=12.8 cudnn=90701
driver=580.97
02:23:57-635596 DEBUG Entering start sequence
02:23:57-638098 DEBUG Initializing
02:23:57-677714 DEBUG Read: file="metadata.json" json=1666 bytes=20785906 time=0.038 fn=initialize:init_metadata
02:23:57-680250 DEBUG Read: file="cache.json" json=2 bytes=416 time=0.000 fn=initialize:init_cache
02:23:57-736003 INFO Available VAEs: path="E:\AI-ImageGen\Database\models\VAE" items=9
02:23:57-737503 INFO Available UNets: path="E:\AI-ImageGen\Database\models\UNET" items=0
02:23:57-738426 INFO Available TEs: path="E:\AI-ImageGen\Database\models\Text-encoder" items=0
02:23:57-744997 INFO Available Models: safetensors="E:\AI-ImageGen\Database\models\Stable-diffusion":14
diffusers="E:\AI-ImageGen\Database\models\Diffusers":13 items=27 time=0.00
02:23:57-841376 INFO Available LoRAs: path="E:\AI-ImageGen\Database\models\Lora" items=790 folders=9 time=0.09
02:23:57-848899 INFO Available Styles: path="E:\AI-ImageGen\Database\models\styles" items=20 time=0.01
02:23:57-943762 INFO Available Detailer: path="E:\AI-ImageGen\Database\models\yolo" items=13 downloaded=3
02:23:57-945252 DEBUG Extensions: disabled=[]
02:23:57-946258 INFO Load extensions
02:23:58-847806 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
02:23:58-890805 DEBUG Read: file="html/upscalers.json" json=4 bytes=2672 time=0.001 fn=__init__:__init__
02:23:58-892780 DEBUG Read: file="extensions-builtin\sd-extension-chainner\models.json" json=25 bytes=2830 time=0.000
fn=__init__:find_scalers
02:23:58-894783 DEBUG Available chaiNNer: path="E:\AI-ImageGen\Database\models\chaiNNer" defined=25 discovered=0
downloaded=24
02:23:58-897280 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN"
model="4x_foolhardy_Remacri"
path="E:\AI-ImageGen\Database\models\ESRGAN\4x_foolhardy_Remacri.pth"
02:23:58-898281 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN"
model="4x_NickelbackFS_72000_G"
path="E:\AI-ImageGen\Database\models\ESRGAN\4x_NickelbackFS_72000_G.pth"
02:23:58-899279 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN" model="ESRGAN 4x
CountryRoads" path="E:\AI-ImageGen\Database\models\ESRGAN\ESRGAN 4x CountryRoads.pth"
02:23:58-903779 INFO Available Upscalers: items=75 downloaded=48 user=3 time=0.02 types=['None', 'Resize', 'Latent',
'AsymmetricVAE', 'DCC', 'VIPS', 'ChaiNNer', 'AuraSR', 'ESRGAN', 'RealESRGAN', 'SCUNet',
'Diffusion', 'SwinIR']
02:23:58-905779 DEBUG Read: file="extensions-builtin\sd-extension-chainner\models.json" json=25 bytes=2830 time=0.000
fn=__init__:find_scalers
02:23:58-908311 DEBUG Available chaiNNer: path="E:\AI-ImageGen\Database\models\chaiNNer" defined=25 discovered=0
downloaded=24
02:23:58-910312 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN"
model="4x_foolhardy_Remacri"
path="E:\AI-ImageGen\Database\models\ESRGAN\4x_foolhardy_Remacri.pth"
02:23:58-911310 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN"
model="4x_NickelbackFS_72000_G"
path="E:\AI-ImageGen\Database\models\ESRGAN\4x_NickelbackFS_72000_G.pth"
02:23:58-912311 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN" model="ESRGAN 4x
CountryRoads" path="E:\AI-ImageGen\Database\models\ESRGAN\ESRGAN 4x CountryRoads.pth"
02:23:58-916782 INFO Available Upscalers: items=75 downloaded=48 user=3 time=0.01 types=['None', 'Resize', 'Latent',
'AsymmetricVAE', 'DCC', 'VIPS', 'ChaiNNer', 'AuraSR', 'ESRGAN', 'RealESRGAN', 'SCUNet',
'Diffusion', 'SwinIR']
02:23:58-932280 DEBUG Read: file="extensions-builtin\sd-extension-chainner\models.json" json=25 bytes=2830 time=0.000
fn=__init__:find_scalers
02:23:58-934278 DEBUG Available chaiNNer: path="E:\AI-ImageGen\Database\models\chaiNNer" defined=25 discovered=0
downloaded=24
02:23:58-936279 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN"
model="4x_foolhardy_Remacri"
path="E:\AI-ImageGen\Database\models\ESRGAN\4x_foolhardy_Remacri.pth"
02:23:58-937282 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN"
model="4x_NickelbackFS_72000_G"
path="E:\AI-ImageGen\Database\models\ESRGAN\4x_NickelbackFS_72000_G.pth"
02:23:58-939811 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN" model="ESRGAN 4x
CountryRoads" path="E:\AI-ImageGen\Database\models\ESRGAN\ESRGAN 4x CountryRoads.pth"
02:23:58-944281 INFO Available Upscalers: items=75 downloaded=48 user=3 time=0.01 types=['None', 'Resize', 'Latent',
'AsymmetricVAE', 'DCC', 'VIPS', 'ChaiNNer', 'AuraSR', 'ESRGAN', 'RealESRGAN', 'SCUNet',
'Diffusion', 'SwinIR']
02:23:58-946378 DEBUG Read: file="extensions-builtin\sd-extension-chainner\models.json" json=25 bytes=2830 time=0.000
fn=__init__:find_scalers
02:23:58-948378 DEBUG Available chaiNNer: path="E:\AI-ImageGen\Database\models\chaiNNer" defined=25 discovered=0
downloaded=24
02:23:58-950378 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN"
model="4x_foolhardy_Remacri"
path="E:\AI-ImageGen\Database\models\ESRGAN\4x_foolhardy_Remacri.pth"
02:23:58-951378 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN"
model="4x_NickelbackFS_72000_G"
path="E:\AI-ImageGen\Database\models\ESRGAN\4x_NickelbackFS_72000_G.pth"
02:23:58-952378 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN" model="ESRGAN 4x
CountryRoads" path="E:\AI-ImageGen\Database\models\ESRGAN\ESRGAN 4x CountryRoads.pth"
02:23:58-956962 INFO Available Upscalers: items=75 downloaded=48 user=3 time=0.01 types=['None', 'Resize', 'Latent',
'AsymmetricVAE', 'DCC', 'VIPS', 'ChaiNNer', 'AuraSR', 'ESRGAN', 'RealESRGAN', 'SCUNet',
'Diffusion', 'SwinIR']
02:23:59-012959 DEBUG Extensions init time: total=1.07 sd-webui-agent-scheduler=0.68 OneButtonPrompt=0.11
cogvideo.py=0.05
02:23:59-014958 DEBUG Read: file="extensions-builtin\sd-extension-chainner\models.json" json=25 bytes=2830 time=0.000
fn=__init__:find_scalers
02:23:59-017457 DEBUG Available chaiNNer: path="E:\AI-ImageGen\Database\models\chaiNNer" defined=25 discovered=0
downloaded=24
02:23:59-019554 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN"
model="4x_foolhardy_Remacri"
path="E:\AI-ImageGen\Database\models\ESRGAN\4x_foolhardy_Remacri.pth"
02:23:59-020517 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN"
model="4x_NickelbackFS_72000_G"
path="E:\AI-ImageGen\Database\models\ESRGAN\4x_NickelbackFS_72000_G.pth"
02:23:59-021547 DEBUG Upscaler type=ESRGAN folder="E:\AI-ImageGen\Database\models\ESRGAN" model="ESRGAN 4x
CountryRoads" path="E:\AI-ImageGen\Database\models\ESRGAN\ESRGAN 4x CountryRoads.pth"
02:23:59-026547 INFO Available Upscalers: items=75 downloaded=48 user=3 time=0.01 types=['None', 'Resize', 'Latent',
'AsymmetricVAE', 'DCC', 'VIPS', 'ChaiNNer', 'AuraSR', 'ESRGAN', 'RealESRGAN', 'SCUNet',
'Diffusion', 'SwinIR']
02:23:59-036015 INFO Huggingface init: transfer=rust parallel=True direct=False token="hf_...rdoQ"
cache="E:\AI-ImageGen\Database\models\huggingface"
02:23:59-114102 WARNING Cache location changed: previous="C:\Users\ohiom\.cache\huggingface\hub" size=21708 MB
02:23:59-156749 DEBUG Huggingface cache: path="E:\AI-ImageGen\Database\models\huggingface" size=476072 MB
02:23:59-157741 DEBUG UI start sequence
02:23:59-158719 INFO UI locale: name="Auto"
02:23:59-159752 INFO UI theme: type=Modern name="Default" available=35
02:23:59-168720 DEBUG UI theme: css="extensions-builtin\sdnext-modernui\themes\Default.css" base="base.css"
user="None"
02:23:59-172229 DEBUG UI initialize: txt2img
02:24:01-140600 DEBUG Networks: type="model" items=27 subfolders=2 tab=txt2img
folders=['E:\\AI-ImageGen\\Database\\models\\Stable-diffusion', 'models\\Reference',
'E:\\AI-ImageGen\\Database\\models\\Stable-diffusion'] list=1.02 thumb=0.44 desc=0.04 info=0.03
workers=12
02:24:01-177627 DEBUG Networks: type="lora" items=790 subfolders=33 tab=txt2img
folders=['E:\\AI-ImageGen\\Database\\models\\Lora'] list=1.82 thumb=0.17 desc=1.38 info=9.67
workers=12
02:24:01-185097 DEBUG Networks: type="style" items=20 subfolders=3 tab=txt2img
folders=['E:\\AI-ImageGen\\Database\\models\\styles', 'html'] list=0.05 thumb=0.04 desc=0.00
info=0.00 workers=12
02:24:01-197120 DEBUG Networks: type="wildcards" items=179 subfolders=6 tab=txt2img
folders=['E:\\AI-ImageGen\\Database\\models\\wildcards'] list=1.94 thumb=0.99 desc=0.00
info=0.00 workers=12
02:24:01-201097 DEBUG Networks: type="embedding" items=55 subfolders=1 tab=txt2img
folders=['E:\\AI-ImageGen\\Database\\models\\embeddings'] list=1.57 thumb=0.44 desc=0.09
info=0.63 workers=12
02:24:01-205624 DEBUG Networks: type="vae" items=9 subfolders=1 tab=txt2img
folders=['E:\\AI-ImageGen\\Database\\models\\VAE'] list=0.65 thumb=0.46 desc=0.00 info=0.10
workers=12
02:24:01-208122 DEBUG Networks: type="history" items=0 subfolders=1 tab=txt2img folders=[] list=0.00 thumb=0.00
desc=0.00 info=0.00 workers=12
02:24:01-518465 DEBUG UI initialize: img2img
02:24:01-826484 DEBUG UI initialize: control models="E:\AI-ImageGen\Database\models\control"
02:24:02-040143 DEBUG Script: fn="extensions-builtin\sd-webui-agent-scheduler\scripts\task_scheduler.py" type=control
skip
02:24:02-041616 DEBUG Script: fn="extensions\sd-dynamic-prompts\scripts\dynamic_prompting.py" type=control skip
02:24:02-157216 DEBUG Script: fn="extensions\OneButtonPrompt\scripts\onebuttonprompt.py" type=control skip
02:24:02-295715 DEBUG UI initialize: video
02:24:02-758623 DEBUG Read: file="ui-config.json" json=7 bytes=389 time=0.000 fn=__init__:read_from_file
02:24:02-764123 DEBUG Settings: sections=24 settings=372/583 quicksettings=0
02:24:04-219398 DEBUG Extension list: processed=412 installed=7 enabled=7 disabled=0 visible=412 hidden=0
02:24:04-851373 DEBUG Root paths: ['E:\\AI-ImageGen\\sdnext_dev', 'models']
02:24:04-957235 INFO Local URL: http://127.0.0.1:7855/
02:24:04-959733 DEBUG API middleware: [<class 'starlette.middleware.base.BaseHTTPMiddleware'>, <class
'starlette.middleware.gzip.GZipMiddleware'>]
02:24:04-961262 DEBUG API initialize
02:24:05-467644 INFO [AgentScheduler] Task queue is empty
02:24:05-487666 INFO [AgentScheduler] Registering APIs
02:24:06-051681 DEBUG Scripts setup: time=0.609 ['One Button Prompt:0.071', 'XYZ Grid:0.059', 'IP Adapters:0.049',
'Prompt enhance:0.031']
02:24:06-052680 DEBUG Model metadata: file="metadata.json" no changes
02:24:06-054680 DEBUG Model requested: fn=threading.py:run:<lambda>
02:24:06-055684 INFO Load model: select="Illustrious - Noob V-Pred 1.0 Personal Merge [d14ea71ad5]"
02:24:06-057681 INFO Autodetect model: detect="Stable Diffusion XL" class=StableDiffusionXLPipeline
file="E:\AI-ImageGen\Database\models\Stable-diffusion\Illustrious - Noob V-Pred 1.0 Personal
Merge.safetensors"
02:24:06-059181 DEBUG Cache clear
Progress 1.56s/it █████████ 100% 7/7 00:10 00:00 Loading pipeline components...
02:24:17-874393 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':
'E:\\AI-ImageGen\\Database\\models\\huggingface'}
02:24:17-877392 INFO Setting override: model="Illustrious - Noob V-Pred 1.0 Personal Merge" component=scheduler
prediction="v-prediction"
02:24:19-305064 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/139.0.0.0 Safari/537.36 Edg/139.0.0.0
02:24:19-427159 DEBUG UI: connected
02:24:22-556596 INFO UI: ready time=15.885
02:24:23-863439 INFO Network load: type=embeddings loaded=19 skipped=36 time=5.98
02:24:23-864940 DEBUG Setting model: component=vae {'slicing': True, 'tiling': True, 'tile': 1024, 'overlap': 0.25}
02:24:23-866438 DEBUG Setting model: attention="Scaled-Dot-Product"
02:24:23-878436 DEBUG Load model: post_quant=sdnq
02:24:23-879937 DEBUG Quantization: type=SDNQ modules=['Model', 'TE'] dtype=int8 dtype_te=Same as model matmul=False
group_size=0 quant_conv=False matmul_conv=False quantize_with_gpu=True dequantize_fp32=False
pre_forward=True
02:24:25-797946 DEBUG GC: current={'gpu': 1.28, 'ram': 8.6, 'oom': 0} prev={'gpu': 1.44, 'ram': 8.6} load={'gpu': 5,
'ram': 7} gc={'gpu': 0.16, 'py': 2811} fn=apply_function_to_model:sdnq_quantize_model why=sdnq
time=0.44
02:24:26-450961 DEBUG GC: current={'gpu': 1.28, 'ram': 7.52, 'oom': 0} prev={'gpu': 1.33, 'ram': 7.52} load={'gpu':
5, 'ram': 6} gc={'gpu': 0.05, 'py': 127} fn=apply_function_to_model:sdnq_quantize_model
why=sdnq time=0.42
02:24:27-282884 DEBUG GC: current={'gpu': 1.28, 'ram': 6.84, 'oom': 0} prev={'gpu': 1.35, 'ram': 6.84} load={'gpu':
5, 'ram': 5} gc={'gpu': 0.07, 'py': 127} fn=apply_function_to_model:sdnq_quantize_model
why=sdnq time=0.39
02:24:27-284391 INFO Quantization: type=SDNQ time=3.40
02:24:27-285890 INFO Offload: type=balanced op=init watermark=0.2-0.8 gpu=4.80-19.20:24.00 cpu=128.000 limit=0.00
always=[] never=['CLIPTextModel', 'CLIPTextModelWithProjection', 'AutoencoderKL']
02:24:27-311888 DEBUG Module: name=unet cls=UNet2DConditionModel size=2.703 params=2567463684 quant=SDNQ
02:24:27-316888 DEBUG Module: name=text_encoder_2 cls=CLIPTextModelWithProjection size=0.708 params=695571200
quant=SDNQ
02:24:27-319889 DEBUG Module: name=vae cls=AutoencoderKL size=0.156 params=83653863 quant=None
02:24:27-322393 DEBUG Module: name=text_encoder cls=CLIPTextModel size=0.151 params=123607296 quant=SDNQ
02:24:27-323890 INFO Model class=StableDiffusionXLPipeline modules=4 size=3.718
02:24:27-327389 INFO Load model: family=sdxl time={'total': 23.35, 'load': 11.82, 'embeddings': 5.99, 'options':
3.42, 'sdnq': 2.08} native=1024 memory={'ram': {'total': 127.92, 'used': 6.84, 'free': 121},
'gpu': {'used': 1.28, 'total': 24.0, 'active': 0.0, 'peak': 0.11, 'retries': 0, 'oom': 0,
'swap': 0}, 'job': 'Load'}
02:24:27-330894 DEBUG Script init: ['task_scheduler.py:ui_tabs=0.37', 'wildcards_tab.py:ui_tabs=0.06',
'system-info.py:app_started=0.31', 'task_scheduler.py:app_started=0.63']
02:24:27-332083 INFO Startup time: total=101.63 checkpoint=21.28 launch=20.39 numpy=20.29 installer=20.21 torch=6.75
ui-networks=2.29 libraries=2.09 ui-extensions=1.45 gradio=1.42 extensions=1.07 app-started=0.95
bnb=0.77 ui-defaults=0.55 ui-control=0.34 ui-txt2img=0.28 ui-img2img=0.25 ui-video=0.15
ui-models=0.15 api=0.14 cleanup=0.12 diffusers=0.11 samplers=0.10 lora=0.10 detailer=0.09
onnx=0.07 ui-extras=0.05
02:24:27-336588 DEBUG Save: file="E:\AI-ImageGen\sdnext_dev\config.json" json=42 bytes=2468 time=0.006
02:24:42-936858 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/139.0.0.0 Safari/537.36 Edg/139.0.0.0
02:24:43-942600 DEBUG UI: connected
02:24:46-890518 INFO UI: ready time=13.7
02:24:52-133271 INFO Settings: changed=1 ['sd_checkpoint_autoload']
02:24:52-137270 DEBUG Save: file="E:\AI-ImageGen\sdnext_dev\config.json" json=43 bytes=2503 time=0.005
02:25:01-520503 INFO Settings: changed=1 ['sdnq_use_quantized_matmul']
02:25:01-524503 DEBUG Save: file="E:\AI-ImageGen\sdnext_dev\config.json" json=44 bytes=2540 time=0.004
02:25:59-137191 INFO Settings: changed=1 ['quicksettings_list']
02:25:59-142195 DEBUG Save: file="E:\AI-ImageGen\sdnext_dev\config.json" json=44 bytes=2563 time=0.005
02:26:27-418874 TRACE Server: alive=True requests=109 memory=6.86/127.92 status='idle' task='' timestamp=None
current='' id='' job=0 jobs=0 total=2 step=0 steps=0 queued=0 uptime=151 elapsed=141.36
eta=None progress=0
02:26:43-278346 INFO Settings: changed=1 ['keep_incomplete']
02:26:43-282350 DEBUG Save: file="E:\AI-ImageGen\sdnext_dev\config.json" json=45 bytes=2591 time=0.004
02:27:49-225068 DEBUG Cache clear
02:27:49-226069 DEBUG Current model: {'ram': {'total': 127.92, 'used': 6.87, 'free': 121}, 'gpu': {'used': 1.28,
'total': 24.0, 'active': 0.0, 'peak': 0.0, 'retries': 0, 'oom': 0, 'swap': 0}, 'job': 'Load'}
02:27:49-838255 DEBUG GC: current={'gpu': 1.28, 'ram': 6.85, 'oom': 0} prev={'gpu': 1.28, 'ram': 6.85} load={'gpu':
5, 'ram': 5} gc={'gpu': 0.0, 'py': 63022} fn=load_model:unload_model_weights why=unload
time=0.46
02:27:49-840255 DEBUG Unload model: {'ram': {'total': 127.92, 'used': 6.85, 'free': 121}, 'gpu': {'used': 1.28,
'total': 24.0, 'active': 0.0, 'peak': 0.0, 'retries': 0, 'oom': 0, 'swap': 0}, 'job': 'Load'}
after
02:27:49-841756 DEBUG Quantization: module="TE" type=sdnq dtype=int8 matmul=True group_size=0 quant_conv=False
matmul_conv=False dequantize_fp32=False quantize_with_gpu=True quantization_device=cuda
return_device=cpu device_map=default offload_mode=balanced non_blocking=False
02:27:50-772285 ERROR video load: module=te cls=T5EncoderModel It looks like the config file at
'E:\AI-ImageGen\Database\models\huggingface\models--Wan-AI--Wan2.2-T2V-A14B-Diffusers\snapshots
\5be7df9619b54f4e2667b2755bc6a756675b5cd7\text_encoder\config.json' is not a valid JSON file.
02:27:50-773827 ERROR video: OSError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\transformers\configuration_utils.py:743 in _get_config_dict │
│ │
│ 742 │ │ │ │ # Load config dict │
│❱ 743 │ │ │ │ config_dict = cls._dict_from_json_file(resolved_config_file) │
│ 744 │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\transformers\configuration_utils.py:845 in _dict_from_json_file │
│ │
│ 844 │ │ │ text = reader.read() │
│❱ 845 │ │ return json.loads(text) │
│ 846 │
│ │
│C:\Users\ohiom\AppData\Local\Programs\Python\Python312\Lib\json\__init__.py:346 in loads │
│ │
│ 345 │ │ │ parse_constant is None and object_pairs_hook is None and not kw): │
│❱ 346 │ │ return _default_decoder.decode(s) │
│ 347 │ if cls is None: │
│ │
│C:\Users\ohiom\AppData\Local\Programs\Python\Python312\Lib\json\decoder.py:338 in decode │
│ │
│ 337 │ │ """ │
│❱ 338 │ │ obj, end = self.raw_decode(s, idx=_w(s, 0).end()) │
│ 339 │ │ end = _w(s, end).end() │
│ │
│C:\Users\ohiom\AppData\Local\Programs\Python\Python312\Lib\json\decoder.py:356 in raw_decode │
│ │
│ 355 │ │ except StopIteration as err: │
│❱ 356 │ │ │ raise JSONDecodeError("Expecting value", s, err.value) from None │
│ 357 │ │ return obj, end │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
JSONDecodeError: Expecting value: line 1 column 1 (char 0)
During handling of the above exception, another exception occurred:
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│E:\AI-ImageGen\sdnext_dev\modules\video_models\video_load.py:28 in load_model │
│ │
│ 27 │ │ debug(f'Video load: module=te repo="{selected.te or selected.repo}" folder="{selected.te_folder}" cls={ │
│❱ 28 │ │ text_encoder = selected.te_cls.from_pretrained( │
│ 29 │ │ │ pretrained_model_name_or_path=selected.te or selected.repo, │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\transformers\modeling_utils.py:317 in _wrapper │
│ │
│ 316 │ │ try: │
│❱ 317 │ │ │ return func(*args, **kwargs) │
│ 318 │ │ finally: │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\transformers\modeling_utils.py:4829 in from_pretrained │
│ │
│ 4828 │ │ │ config_path = config if config is not None else pretrained_model_name_or_path │
│❱ 4829 │ │ │ config, model_kwargs = cls.config_class.from_pretrained( │
│ 4830 │ │ │ │ config_path, │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\transformers\configuration_utils.py:609 in from_pretrained │
│ │
│ 608 │ │ │
│❱ 609 │ │ config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) │
│ 610 │ │ if cls.base_config_key and cls.base_config_key in config_dict: │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\transformers\configuration_utils.py:649 in get_config_dict │
│ │
│ 648 │ │ # Get config dict associated with the base config file │
│❱ 649 │ │ config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) │
│ 650 │ │ if config_dict is None: │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\transformers\configuration_utils.py:747 in _get_config_dict │
│ │
│ 746 │ │ except (json.JSONDecodeError, UnicodeDecodeError): │
│❱ 747 │ │ │ raise OSError(f"It looks like the config file at '{resolved_config_file}' is not a valid JSON file │
│ 748 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
OSError: It looks like the config file at 'E:\AI-ImageGen\Database\models\huggingface\models--Wan-AI--Wan2.2-T2V-A14B-Diffusers\snapshots\5be7df9619b54f4e2667b2755bc6a756675b5cd7\text_encoder\config.json' is not a valid JSON file.
02:27:51-506231 DEBUG Quantization: module="Model" type=sdnq dtype=int8 matmul=True group_size=0 quant_conv=False
matmul_conv=False dequantize_fp32=False quantize_with_gpu=True quantization_device=cuda
return_device=cpu device_map=default offload_mode=balanced non_blocking=False
Progress ?it/s ████████████████████████████ 100% 12/12 00:00 ? Fetching 12 files
Progress 3.64s/it █████████▊ 75% 9/12 00:31 00:10 Loading checkpoint shards02:28:27-839033 TRACE Server: alive=True requests=210 memory=20.65/127.92 status='idle' task='' timestamp=None
current='task(h8n3v5o6e7m2urf)' id='' job=0 jobs=0 total=2 step=0 steps=0 queued=0 uptime=271
elapsed=261.78 eta=None progress=0
Progress 3.64s/it ████████████ 100% 12/12 00:43 00:00 Loading checkpoint shards
02:28:36-931087 DEBUG GC: current={'gpu': 1.28, 'ram': 19.25, 'oom': 0} prev={'gpu': 1.28, 'ram': 19.25} load={'gpu':
5, 'ram': 15} gc={'gpu': 0.0, 'py': 567}
fn=postprocess_model:_process_model_after_weight_loading why=sdnq time=0.45
02:28:37-676747 ERROR video load: module=pipe repo="Wan-AI/Wan2.2-T2V-A14B-Diffusers" cls=WanPipeline Expecting
value: line 1 column 1 (char 0)
02:28:37-678246 ERROR video: JSONDecodeError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│E:\AI-ImageGen\sdnext_dev\modules\video_models\video_load.py:64 in load_model │
│ │
│ 63 │ │ debug(f'Video load: module=pipe repo="{selected.repo}" cls={selected.repo_cls.__name__}') │
│❱ 64 │ │ shared.sd_model = selected.repo_cls.from_pretrained( │
│ 65 │ │ │ pretrained_model_name_or_path=selected.repo, │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:114 in _inner_fn │
│ │
│ 113 │ │ │
│❱ 114 │ │ return fn(*args, **kwargs) │
│ 115 │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\diffusers\pipelines\pipeline_utils.py:833 in from_pretrained │
│ │
│ 832 │ │ │ │ ) │
│❱ 833 │ │ │ cached_folder = cls.download( │
│ 834 │ │ │ │ pretrained_model_name_or_path, │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:114 in _inner_fn │
│ │
│ 113 │ │ │
│❱ 114 │ │ return fn(*args, **kwargs) │
│ 115 │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\diffusers\pipelines\pipeline_utils.py:1499 in download │
│ │
│ 1498 │ │ │ ) │
│❱ 1499 │ │ │ config_dict = cls._dict_from_json_file(config_file) │
│ 1500 │ │ │ ignore_filenames = config_dict.pop("_ignore_files", []) │
│ │
│E:\AI-ImageGen\sdnext_dev\venv\Lib\site-packages\diffusers\configuration_utils.py:574 in _dict_from_json_file │
│ │
│ 573 │ │ │ │ text = reader.read() │
│❱ 574 │ │ return json.loads(text) │
│ 575 │
│ │
│C:\Users\ohiom\AppData\Local\Programs\Python\Python312\Lib\json\__init__.py:346 in loads │
│ │
│ 345 │ │ │ parse_constant is None and object_pairs_hook is None and not kw): │
│❱ 346 │ │ return _default_decoder.decode(s) │
│ 347 │ if cls is None: │
│ │
│C:\Users\ohiom\AppData\Local\Programs\Python\Python312\Lib\json\decoder.py:338 in decode │
│ │
│ 337 │ │ """ │
│❱ 338 │ │ obj, end = self.raw_decode(s, idx=_w(s, 0).end()) │
│ 339 │ │ end = _w(s, end).end() │
│ │
│C:\Users\ohiom\AppData\Local\Programs\Python\Python312\Lib\json\decoder.py:356 in raw_decode │
│ │
│ 355 │ │ except StopIteration as err: │
│❱ 356 │ │ │ raise JSONDecodeError("Expecting value", s, err.value) from None │
│ 357 │ │ return obj, end │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
JSONDecodeError: Expecting value: line 1 column 1 (char 0)
02:28:37-972165 DEBUG Model requested: fn=video_run.py:generate:load_model
02:28:37-973386 INFO Load model: select="Illustrious - Noob V-Pred 1.0 Personal Merge [d14ea71ad5]"
02:28:37-975393 INFO Autodetect model: detect="Stable Diffusion XL" class=StableDiffusionXLPipeline
file="E:\AI-ImageGen\Database\models\Stable-diffusion\Illustrious - Noob V-Pred 1.0 Personal
Merge.safetensors"
02:28:37-976890 DEBUG Cache clear
Progress 1.28it/s █████████ 100% 7/7 00:05 00:00 Loading pipeline components...
02:28:44-400095 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':
'E:\\AI-ImageGen\\Database\\models\\huggingface'}
02:28:44-403598 INFO Setting override: model="Illustrious - Noob V-Pred 1.0 Personal Merge" component=scheduler
prediction="v-prediction"
02:28:50-202554 INFO Network load: type=embeddings loaded=19 skipped=36 time=5.80
02:28:50-204057 DEBUG Setting model: component=vae {'slicing': True, 'tiling': True, 'tile': 1024, 'overlap': 0.25}
02:28:50-205568 DEBUG Setting model: attention="Scaled-Dot-Product"
02:28:50-216570 DEBUG Load model: post_quant=sdnq
02:28:50-218070 DEBUG Quantization: type=SDNQ modules=['Model', 'TE'] dtype=int8 dtype_te=Same as model matmul=True
group_size=0 quant_conv=False matmul_conv=False quantize_with_gpu=True dequantize_fp32=False
pre_forward=True
02:28:52-502010 DEBUG GC: current={'gpu': 1.28, 'ram': 22.41, 'oom': 0} prev={'gpu': 1.44, 'ram': 22.41} load={'gpu':
5, 'ram': 18} gc={'gpu': 0.16, 'py': 179} fn=apply_function_to_model:sdnq_quantize_model
why=sdnq time=0.50
02:28:53-057632 DEBUG GC: current={'gpu': 1.28, 'ram': 22.48, 'oom': 0} prev={'gpu': 1.33, 'ram': 22.48} load={'gpu':
5, 'ram': 18} gc={'gpu': 0.05, 'py': 127} fn=apply_function_to_model:sdnq_quantize_model
why=sdnq time=0.45
02:28:54-179139 DEBUG GC: current={'gpu': 1.28, 'ram': 20.03, 'oom': 0} prev={'gpu': 1.35, 'ram': 20.03} load={'gpu':
5, 'ram': 16} gc={'gpu': 0.07, 'py': 138} fn=apply_function_to_model:sdnq_quantize_model
why=sdnq time=0.42
02:28:54-182140 INFO Quantization: type=SDNQ time=3.96
02:28:54-183140 INFO Offload: type=balanced op=init watermark=0.2-0.8 gpu=4.80-19.20:24.00 cpu=128.000 limit=0.00
always=[] never=['CLIPTextModel', 'CLIPTextModelWithProjection', 'AutoencoderKL']
02:28:54-213670 DEBUG Module: name=unet cls=UNet2DConditionModel size=2.703 params=2567463684 quant=SDNQ
02:28:54-218669 DEBUG Module: name=text_encoder_2 cls=CLIPTextModelWithProjection size=0.708 params=695571200
quant=SDNQ
02:28:54-222140 DEBUG Module: name=vae cls=AutoencoderKL size=0.156 params=83653863 quant=None
02:28:54-225169 DEBUG Module: name=text_encoder cls=CLIPTextModel size=0.151 params=123607296 quant=SDNQ
02:28:54-226170 INFO Model class=StableDiffusionXLPipeline modules=4 size=3.718
02:28:54-230166 INFO Load model: family=sdxl time={'total': 18.77, 'load': 6.43, 'embeddings': 5.8, 'options': 3.98,
'sdnq': 2.51} native=1024 memory={'ram': {'total': 127.92, 'used': 20.03, 'free': 108}, 'gpu':
{'used': 1.28, 'total': 24.0, 'active': 0.0, 'peak': 0.59, 'retries': 0, 'oom': 0, 'swap': 0},
'job': 'Load'}
02:28:54-232641 DEBUG Setting model: component=vae {'slicing': True, 'tiling': True, 'tile': 1024, 'overlap': 0.25}
02:28:54-234139 DEBUG Setting model: attention="Scaled-Dot-Product"
02:28:54-245170 INFO Offload: type=balanced op=init watermark=0.2-0.8 gpu=4.80-19.20:24.00 cpu=128.000 limit=0.00
always=[] never=['CLIPTextModel', 'CLIPTextModelWithProjection', 'AutoencoderKL']
02:28:54-274158 DEBUG Module: name=unet cls=UNet2DConditionModel size=2.703 params=2567463684 quant=SDNQ
02:28:54-279168 DEBUG Module: name=text_encoder_2 cls=CLIPTextModelWithProjection size=0.708 params=695571200
quant=SDNQ
02:28:54-283169 DEBUG Module: name=vae cls=AutoencoderKL size=0.156 params=83653863 quant=None
02:28:54-284167 TRACE State history: uptime=297 jobs=10 tasks=0 latents=0 images=0
02:28:54-287197 DEBUG Module: name=text_encoder cls=CLIPTextModel size=0.151 params=123607296 quant=SDNQ
02:28:54-288667 INFO Exiting
02:28:54-289168 INFO Model class=StableDiffusionXLPipeline modules=4 size=3.718
02:28:54-290710 INFO Video load: cls=StableDiffusionXLPipeline model="WAN 2.2 A14B I2V" time=48.13
forrtl: error (200): program aborting due to control-C event
Backend
Diffusers
Compute
nVidia CUDA
Interface
ModernUI
Branch
Dev
Model
Other
Acknowledgements
- [x] I have read the above and searched for existing issues
- [x] I confirm that this is classified correctly and its not an extension issue
i understand the issue, but handling of that is extremely messy. if model is not loaded, it can be pulled by any operation. and since last known model was sdxl in base, that's what gets pulled.
only thing i dont understand it this statement:
and forcing a weird state where futher video attempts are unsuccesfull, only resolved by restart:
you can use that base model in txt/img/control tabs or if you want to use video tab, load a video model. the fact that all this happened does not change that. as soon as you sucessfully load a video model, it should all be good. no server restart needed.
anyhow, i'm putting this in a backlog for now.
