[Issue]: SD.next report conv2d error and halts generating when launching animatediff. #4518
Description
Issue Description
My laptop can’t launch FramePack because it does not have a DGPU. Instead, I had launched Animatediff at SD.next, but it crashed and reported a conv2d error. according to grok analyze, exisiting diffuser pipleline is crashed with animatediff pipeline.
Version Platform Description
AMD ryzen ai 340, radeon 840m, 32gb ddr5
Relevant log output
PS C:\ai\sdnext> .\webui-user.bat
23:50:03-807616 INFO Starting SD.Next
23:50:03-810620 INFO Logger: file="C:\ai\sdnext\sdnext.log" level=DEBUG host="DESKTOP-SGFT5T6" size=83 mode=create
23:50:03-812619 INFO Python: version=3.11.9 platform=Windows
bin="C:\Users\winbbs\AppData\Local\Programs\Python\Python311\python.exe"
venv="C:\Users\winbbs\AppData\Local\Programs\Python\Python311"
23:50:04-187069 INFO Version: app=sd.next updated=2026-01-01 commit=98d304a49 branch=dev
url=https://github.com/vladmandic/sdnext/tree/dev kanvas=main ui=dev
23:50:05-048739 TRACE Repository branches: active=dev available=['dev', 'master', 'upstream']
23:50:05-357751 INFO Version: app=sd.next latest=2026-01-01T10:22:43Z hash=98d304a4 branch=dev
23:50:05-370753 INFO Platform: arch=AMD64 cpu=AMD64 Family 26 Model 96 Stepping 0, AuthenticAMD system=Windows
release=Windows-10-10.0.26200-SP0 python=3.11.9 locale=('Korean_Korea', '949') docker=False
23:50:05-372757 DEBUG Packages: prefix=..\..\Users\winbbs\AppData\Local\Programs\Python\Python311
site=['..\\..\\Users\\winbbs\\AppData\\Local\\Programs\\Python\\Python311',
'..\\..\\Users\\winbbs\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages']
23:50:05-373753 INFO Args: ['--use-openvino', '--update']
23:50:05-374757 DEBUG Setting environment tuning
23:50:05-375753 DEBUG Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
23:50:05-376751 INFO Verifying torch installation
23:50:05-377751 DEBUG Torch overrides: cuda=False rocm=False ipex=False directml=False openvino=True zluda=False
23:50:05-378756 INFO OpenVINO: selected
23:50:08-851620 INFO Install: verifying requirements
23:50:08-865623 INFO Startup: standard
23:50:08-866622 INFO Verifying submodules
23:50:11-967331 DEBUG Git submodule: extensions-builtin/sd-extension-chainner / main
23:50:13-000186 DEBUG Git submodule: extensions-builtin/sd-extension-system-info / main
23:50:14-096793 DEBUG Git submodule: extensions-builtin/sdnext-kanvas / main
23:50:15-254761 DEBUG Git submodule: extensions-builtin/sdnext-modernui / dev
23:50:16-483354 DEBUG Git submodule: extensions-builtin/stable-diffusion-webui-rembg / master
23:50:17-610514 DEBUG Git submodule: wiki / master
23:50:18-592488 DEBUG Installed packages: 284
23:50:18-594613 DEBUG Extensions all: ['sd-extension-chainner', 'sd-extension-system-info',
'sd-webui-agent-scheduler', 'sdnext-kanvas', 'sdnext-modernui', 'stable-diffusion-webui-rembg']
23:50:18-694966 DEBUG Git submodule: extensions-builtin\sd-extension-chainner / main
23:50:19-810119 DEBUG Git submodule: extensions-builtin\sd-extension-system-info / main
23:50:21-845470 ERROR Git: folder="extensions-builtin\sd-webui-agent-scheduler" could not identify repository
23:50:22-008982 DEBUG Git submodule: extensions-builtin\sdnext-kanvas / main
23:50:23-200422 DEBUG Git submodule: extensions-builtin\sdnext-modernui / dev
23:50:24-429407 DEBUG Git submodule: extensions-builtin\stable-diffusion-webui-rembg / master
23:50:25-314396 DEBUG Extension installer: builtin=True
file="C:\ai\sdnext\extensions-builtin\stable-diffusion-webui-rembg\install.py"
23:50:25-379327 DEBUG Extensions all: []
23:50:25-380331 INFO Extensions enabled: ['sd-extension-chainner', 'sd-extension-system-info',
'sd-webui-agent-scheduler', 'sdnext-kanvas', 'sdnext-modernui', 'stable-diffusion-webui-rembg']
23:50:25-446836 INFO Install: verifying requirements
23:50:25-450510 INFO Updating Wiki
23:50:25-544435 DEBUG Git submodule: C:\ai\sdnext\wiki / master
23:50:26-489975 WARNING Setup complete with errors: ['git: extensions-builtin\\sd-webui-agent-scheduler']
23:50:26-490975 WARNING See log file for more details: C:\ai\sdnext\sdnext.log
23:50:26-494979 DEBUG Extension preload: {'extensions-builtin': 0.0, 'extensions': 0.0}
23:50:26-495975 INFO Installer time: total=56.35 git=17.33 update=14.12 submodules=9.66 torch=3.23 latest=1.54
branch=1.44 sdnext-modernui=1.24 sdnext-kanvas=1.19 sd-extension-system-info=1.14
sd-extension-chainner=1.12 sd-webui-agent-scheduler=1.06 stable-diffusion-webui-rembg=1.05
wiki=1.04 base=0.37 version=0.36 files=0.18 requirements=0.14 installed=0.13
23:50:26-497974 INFO Command line args: ['--use-openvino', '--update'] upgrade=True use_openvino=True args=[]
23:50:26-497974 DEBUG Env flags: []
23:50:26-498975 DEBUG Starting module: <module 'webui' from 'C:\\ai\\sdnext\\webui.py'>
23:50:58-122529 INFO Torch: torch==2.6.0+cpu torchvision==0.21.0+cpu
23:50:58-125530 INFO Packages: diffusers==0.36.0.dev0 transformers==4.57.3 accelerate==1.12.0 gradio==3.43.2
pydantic==1.10.21 numpy==2.1.2 cv2==4.12.0
HIP Library Path: C:\WINDOWS\System32\amdhip64_7.dll
23:50:58-895829 DEBUG ONNX: version=1.22.1, available=['AzureExecutionProvider', 'CPUExecutionProvider']
23:50:59-267699 DEBUG State initialized: id=2110282198864
23:51:00-067941 WARNING GPU stats: Torch not compiled with CUDA enabled
23:51:00-068944 DEBUG Triton: pass=False fn=<module>:has_triton time=0.00
23:51:00-201225 DEBUG Read: file="C:\ai\sdnext\config.json" json=28 bytes=1089 time=0.000 fn=<module>:load
23:51:00-203226 INFO Engine: backend=Backend.DIFFUSERS compute=openvino device=cpu attention="Scaled-Dot-Product"
mode=no_grad
23:51:00-213228 DEBUG Read: file="html\reference.json" json=151 bytes=72399 time=0.009
fn=_call_with_frames_removed:<module>
23:51:00-214227 DEBUG Torch attention: type="sdpa" kernels=['Flash', 'Memory', 'Math'] overrides=[]
23:51:00-216228 DEBUG Torch attention installed: flashattn=False sageattention=False
23:51:00-216228 WARNING Torch SDPA: module 'diffusers.models.attention_dispatch' has no attribute '_CAN_USE_AITER_ATTN'
23:51:00-217231 DEBUG Triton: pass=False fn=<module>:set_cuda_params time=0.00
23:51:00-234417 WARNING OpenVINO: device=CPU no compatible GPU detected
23:51:00-237415 INFO Torch parameters: backend=openvino device=CPU config=FP32 dtype=torch.float32 context=no_grad
nohalf=False nohalfvae=False upcast=False deterministic=False tunable=[False, False] fp16=fail
bf16=fail triton=fail optimization="Scaled-Dot-Product"
23:51:00-249411 DEBUG Quantization: registered=SDNQ
23:51:00-273410 INFO Device: device=AMD Ryzen AI 5 340 w/ Radeon 840M openvino=2026.0.0.dev20251128
23:51:00-674304 DEBUG Entering start sequence
23:51:00-680112 DEBUG Initializing
23:51:00-689114 DEBUG Read: file="metadata.json" json=2 bytes=1546 time=0.008 fn=initialize:init_metadata
23:51:00-698111 DEBUG Read: file="cache.json" json=1 bytes=350 time=0.007 fn=initialize:init_cache
23:51:00-756203 INFO Available VAEs: path="models\VAE" items=0
23:51:00-758203 INFO Available UNets: path="models\UNET" items=0
23:51:00-759201 INFO Available TEs: path="models\Text-encoder" items=0
23:51:00-766440 INFO Available Models: safetensors="models\Stable-diffusion":2 diffusers="models\Diffusers":3
reference=151 items=5 time=0.00
23:51:00-780442 INFO Available LoRAs: path="models\Lora" items=0 folders=2 time=0.00
23:51:01-591721 INFO Available Styles: path="models\styles" items=288 time=0.81
23:51:01-698771 INFO Available Detailer: path="models\yolo" items=15 downloaded=7
23:51:01-700778 DEBUG Extensions: disabled=['sdnext-modernui']
23:51:01-701770 INFO Load extensions
23:51:01-979355 DEBUG Extensions init time: total=0.28
23:51:02-267128 DEBUG Read: file="html/upscalers.json" json=4 bytes=2672 time=0.011 fn=__init__:__init__
23:51:02-279992 DEBUG Read: file="extensions-builtin\sd-extension-chainner\models.json" json=25 bytes=2830 time=0.010
fn=__init__:find_scalers
23:51:02-282257 DEBUG Available chaiNNer: path="models\chaiNNer" defined=25 discovered=0 downloaded=0
23:51:02-286244 INFO Available Upscalers: items=76 downloaded=0 user=0 time=0.30 types=['None', 'Resize', 'Latent',
'AsymmetricVAE', 'WanUpscale', 'DCC', 'VIPS', 'ChaiNNer', 'AuraSR', 'ESRGAN', 'RealESRGAN',
'SCUNet', 'Diffusion', 'SeedVR', 'SwinIR']
23:51:02-337878 INFO Networks: type="video" engines=13 models=67 errors=0 time=0.04
23:51:02-342525 INFO Huggingface: transfer=rust parallel=True direct=False token="None" cache="models\huggingface"
init
23:51:02-359253 WARNING Cache location changed: previous="C:\Users\winbbs\.cache\huggingface\hub" size=3657 MB
23:51:02-368253 DEBUG Huggingface: cache="models\huggingface" size=7682 MB
23:51:02-369254 DEBUG UI start sequence
23:51:02-370396 DEBUG UI image support: kanvas=main
23:51:02-395168 INFO UI locale: name="Auto"
23:51:02-396166 INFO UI theme: type=Standard name="black-teal" available=14
23:51:02-398166 DEBUG UI theme: css="C:\ai\sdnext\javascript\black-teal.css" base="['sdnext.css', 'timesheet.css']"
user="None"
23:51:02-401167 DEBUG UI initialize: tab=txt2img
23:51:02-443120 DEBUG Read: file="html\reference.json" json=151 bytes=72399 time=0.001 fn=list_items:list_reference
23:51:02-464918 DEBUG Networks: type="reference" items={'total': 151, 'ready': 0, 'hidden': 0, 'experimental': 0,
'base': 95, 'distilled': 18, 'quantized': 19, 'community': 15, 'cloud': 2}
23:51:02-473917 DEBUG Networks: type="model" items=154 subfolders=8 tab=txt2img folders=['models\\Stable-diffusion',
'models\\Reference', 'C:\\ai\\sdnext\\models\\Stable-diffusion'] list=0.06 thumb=0.00 desc=0.00
info=0.01 workers=12
23:51:02-475917 DEBUG Networks: type="lora" items=0 subfolders=1 tab=txt2img folders=['models\\Lora'] list=0.01
thumb=0.00 desc=0.00 info=0.00 workers=12
23:51:02-484917 DEBUG Networks: type="style" items=288 subfolders=3 tab=txt2img folders=['models\\styles', 'html']
list=0.02 thumb=0.00 desc=0.00 info=0.00 workers=12
23:51:02-487214 DEBUG Networks: type="wildcards" items=0 subfolders=1 tab=txt2img folders=['models\\wildcards']
list=0.00 thumb=0.00 desc=0.00 info=0.00 workers=12
23:51:02-489214 DEBUG Networks: type="embedding" items=3 subfolders=1 tab=txt2img folders=['models\\embeddings']
list=0.01 thumb=0.00 desc=0.00 info=0.00 workers=12
23:51:02-490213 DEBUG Networks: type="vae" items=0 subfolders=1 tab=txt2img folders=['models\\VAE'] list=0.00
thumb=0.00 desc=0.00 info=0.00 workers=12
23:51:02-492212 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
23:51:02-604930 DEBUG UI initialize: tab=img2img
23:51:03-042415 DEBUG UI initialize: tab=control models="models\control"
23:51:03-268370 DEBUG UI initialize: tab=video
23:51:03-347108 DEBUG UI initialize: tab=process
23:51:03-373586 DEBUG UI initialize: tab=caption
23:51:03-503931 DEBUG UI initialize: tab=models
23:51:03-547738 DEBUG UI initialize: tab=gallery
23:51:03-571199 DEBUG Read: file="ui-config.json" json=0 bytes=2 time=0.000 fn=__init__:read_from_file
23:51:03-572201 DEBUG UI initialize: tab=settings
23:51:03-576198 ERROR Pipeline=HunyuanImage diffusers=0.36.0.dev0
path=C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\__init
__.py not available
23:51:03-577198 ERROR Pipeline=Z-Image diffusers=0.36.0.dev0
path=C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\__init
__.py not available
23:51:03-578198 ERROR Pipeline=LongCat diffusers=0.36.0.dev0
path=C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\__init
__.py not available
23:51:03-814838 DEBUG Settings: sections=23 settings=387/601 quicksettings=1
23:51:03-856822 DEBUG UI initialize: tab=info
23:51:03-869820 DEBUG UI initialize: tab=extensions
23:51:03-872819 INFO Extension List: No information found. Refresh required.
23:51:04-457539 DEBUG Extension list: processed=4 installed=4 enabled=4 disabled=0 visible=4 hidden=0
23:51:04-942178 DEBUG Root paths: ['C:\\ai\\sdnext', 'models']
23:51:05-043821 INFO Local URL: http://127.0.0.1:7860/
23:51:05-045821 INFO API docs: http://127.0.0.1:7860/docs
23:51:05-046820 INFO API redocs: http://127.0.0.1:7860/redocs
23:51:05-049783 DEBUG API middleware: [<class 'starlette.middleware.base.BaseHTTPMiddleware'>, <class
'starlette.middleware.gzip.GZipMiddleware'>]
23:51:05-050787 DEBUG API initialize
23:51:05-200549 DEBUG Scripts setup: time=0.210 []
23:51:05-201550 DEBUG Model metadata: file="metadata.json" no changes
23:51:05-202549 INFO Model: autoload=True selected="AnythingXL_xl [8421598e93]"
23:51:05-204553 DEBUG Model requested: fn=threading.py:run:<lambda>
23:51:05-205551 DEBUG Search model: name="AnythingXL_xl [8421598e93]"
matched="C:\ai\sdnext\models\Stable-diffusion\AnythingXL_xl.safetensors" type=alias
23:51:05-206226 INFO Load model: select="AnythingXL_xl [8421598e93]"
23:51:05-208234 ERROR Pipeline=HunyuanImage diffusers=0.36.0.dev0
path=C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\__init
__.py not available
23:51:05-208234 ERROR Pipeline=Z-Image diffusers=0.36.0.dev0
path=C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\__init
__.py not available
23:51:05-209233 ERROR Pipeline=LongCat diffusers=0.36.0.dev0
path=C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\__init
__.py not available
23:51:05-210238 INFO Autodetect model: detect="Stable Diffusion XL" class=StableDiffusionXLPipeline
file="C:\ai\sdnext\models\Stable-diffusion\AnythingXL_xl.safetensors"
23:51:05-211234 DEBUG Cache clear
Progress 1.24s/it █████████ 100% 7/7 00:08 00:00 Loading pipeline components...
23:51:15-152861 DEBUG Setting model: pipeline=StableDiffusionXLPipeline config={'low_cpu_mem_usage': True,
'torch_dtype': torch.float32, 'load_connected_pipeline': True, 'extract_ema': False, 'config':
'configs/sdxl', 'use_safetensors': True, 'cache_dir': 'models\\huggingface'}
23:51:15-253376 INFO Network load: type=embeddings loaded=0 skipped=3 time=0.08
23:51:15-255373 DEBUG Setting model: component=vae {'slicing': True, 'tiling': False}
23:51:15-256372 DEBUG Setting model: attention="Scaled-Dot-Product"
23:51:15-258372 DEBUG Setting model: offload=none limit=0.0
23:51:15-260372 INFO Model compile: pipeline=StableDiffusionXLPipeline mode=default backend=openvino_fx options=[]
compile=['Model', 'VAE', 'Upscaler', 'Control']
23:51:15-263371 DEBUG Model compile: task=torch backends=['cudagraphs', 'inductor', 'onnxrt', 'openvino',
'openvino_fx', 'openxla', 'tvm']
23:51:15-342376 INFO Model compile: task=torch time=0.08
23:51:16-040639 DEBUG GC: current={'gpu': 0, 'ram': 23.47, 'oom': 0} prev={'gpu': 0, 'ram': 23.39} load={'gpu': 0,
'ram': 77} gc={'gpu': 0, 'py': 6548} fn=reload_model_weights:load_diffuser why=load time=0.70
23:51:16-043639 INFO Load model: family=sdxl time={'total': 10.14, 'load': 9.97} native=1024 memory={'ram':
{'total': 30.52, 'rss': 11.96, 'used': 23.47, 'free': 7.05, 'avail': 7.05, 'buffers': 0,
'cached': 0}, 'gpu': {'total': 0, 'used': 0, 'error': 'Torch not compiled with CUDA enabled',
'swap': 0}, 'job': 'Load model'}
23:51:16-049150 DEBUG Script init: ['system-info.py:app_started=0.08']
23:51:16-051152 INFO Startup time: total=119.05 launch=23.69 loader=23.17 installer=23.17 torch=22.57
checkpoint=10.85 diffusers=4.39 gradio=3.54 libraries=3.20 ui-extensions=0.88 styles=0.81
ui-networks=0.56 upscalers=0.31 extensions=0.28 numpy=0.20 ui-control=0.15 ui-models=0.15
cv2=0.15 detailer=0.11
23:51:16-063653 DEBUG Save: file="C:\ai\sdnext\config.json" json=28 bytes=1058 time=0.015
23:52:47-849024 DEBUG UI: connected
23:52:47-852026 INFO API user=None code=200 http/1.1 GET /sdapi/v1/version 127.0.0.1 0.004
23:53:16-114285 TRACE Server: alive=True requests=8 memory=23.88/30.52 status='idle' task='' timestamp=None
current='' id='' job=0 jobs=0 total=2 step=0 steps=0 queued=0 uptime=137 elapsed=120.06
eta=None progress=0
23:53:42-816881 DEBUG Control image: upload=<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=1200x1200 at
0x1EB61667B50>
path="C:\Users\winbbs\AppData\Local\Temp\gradio\d919e383a72950679031ed7f535559c53091ad7b\00823-
2026-01-01-AnythingXL_xl.jpg"
23:54:01-493035 DEBUG Kanvas: image=<PIL.Image.Image image mode=RGB size=1519x1200 at 0x1EB61309010>:1961430
mask=None:0 time=0.03
23:54:01-495040 DEBUG Select input: type=Kanvas source=[<PIL.Image.Image image mode=RGB size=1519x1200 at
0x1EB61309010>] init=None mask=None mode=Kanvas time=0.03
23:54:04-288171 DEBUG Control Processor loaded: id="OpenPose" class=OpenposeDetector time=1.89
23:54:04-289170 DEBUG Control ControlNet model loading: id="OpenPose XL"
path="thibaud/controlnet-openpose-sdxl-1.0/bin"
23:54:04-959644 DEBUG Control compile: task=torch backends=['cudagraphs', 'inductor', 'onnxrt', 'openvino',
'openvino_fx', 'openxla', 'tvm']
23:54:04-979645 INFO Control compile: task=torch time=0.02
23:54:04-981644 INFO Control ControlNet model loaded: id="OpenPose XL" path="thibaud/controlnet-openpose-sdxl-1.0"
cls=ControlNetModel time=0.69
23:54:04-982644 DEBUG Control unit: i=1 type=ControlNet process="OpenPose" model="OpenPose XL" strength=1 guess=False
start=0 end=1 mode=default
23:54:04-984644 DEBUG Setting model: offload=none limit=0.0
23:54:04-985644 DEBUG Setting model: component=vae {'slicing': True, 'tiling': False}
23:54:04-985644 DEBUG Setting model: attention="Scaled-Dot-Product"
23:54:04-986644 DEBUG Setting model: offload=none limit=0.0
23:54:04-997456 DEBUG Image resize: source=1200:1200 target=1519:1200 mode="Fixed" upscaler="None" type=image
time=0.01 fn=preprocess_image:__call__
23:54:05-576971 DEBUG Control Processor: id="OpenPose" mode=RGB args={'include_body': True, 'include_hand': False,
'include_face': False} time=0.58
23:54:05-581973 DEBUG Pipeline class change: original=StableDiffusionXLControlNetPipeline
target=StableDiffusionXLControlNetImg2ImgPipeline device=cpu fn=control_run:preprocess_image
23:54:05-603971 INFO AnimateDiff load: adapter="a-r-r-o-w/animatediff-motion-adapter-sdxl-beta"
23:54:06-856725 DEBUG Setting model: attention="Scaled-Dot-Product"
23:54:06-859725 DEBUG Setting adapter: offload=none limit=0.0
23:54:06-868725 DEBUG Setting model: component=vae {'slicing': True, 'tiling': False}
23:54:06-869725 DEBUG Setting model: attention="Scaled-Dot-Product"
23:54:06-870725 DEBUG Setting model: offload=none limit=0.0
23:54:06-871725 DEBUG AnimateDiff: adapter="a-r-r-o-w/animatediff-motion-adapter-sdxl-beta"
23:54:06-873725 DEBUG AnimateDiff: scheduler=DDIMScheduler
23:54:06-874726 DEBUG AnimateDiff args: {'controlnet_conditioning_scale': 1.0, 'control_guidance_start': 0.0,
'control_guidance_end': 1.0, 'guess_mode': False, 'generator': None, 'num_frames': 16,
'num_inference_steps': 20, 'output_type': 'np'}
23:54:06-875726 DEBUG AnimateDiff prompt: masterpiece, front view, 1girl, standing, flower field, The dress covers
the shoulders with a white flower, and the chest and belly are hidden under a pink fabric,
skirt resembles like is bud and each edge has pointed, translucent pink fabric covers her head,
purple eyes, blue hair, upper body close to the camera, occupying the foreground
23:54:06-891725 DEBUG Sampler: "Default" cls=EulerAncestralDiscreteScheduler config={'num_train_timesteps': 1000,
'beta_start': 0.00085, 'beta_end': 0.012, 'beta_schedule': 'scaled_linear', 'trained_betas':
None, 'prediction_type': 'epsilon', 'timestep_spacing': 'trailing', 'steps_offset': 1,
'rescale_betas_zero_snr': False, 'interpolation_type': 'linear', 'use_karras_sigmas': False,
'clip_sample': False, 'sample_max_value': 1.0, 'set_alpha_to_one': False, 'skip_prk_steps':
True}
23:54:06-971234 INFO Processing modifiers: apply
23:54:06-994234 DEBUG Setting model: offload=none limit=0.0
23:54:07-185761 INFO Base: pipeline=AnimateDiffSDXLPipeline task=TEXT_2_IMAGE batch=1/1x1 set={'prompt': 340,
'negative_prompt': 147, 'guidance_scale': 6, 'generator': 'cpu:[1585077217]',
'num_inference_steps': 20, 'eta': 1.0, 'guidance_rescale': 0, 'denoising_end': None,
'num_frames': 16, 'output_type': 'np', 'parser': 'fixed'}
Progress ?it/s 0% 0/20 00:01 ? Base
23:54:09-493079 ERROR Processing: step=base args={'prompt': 'masterpiece, front view, 1girl, standing, flower field,
The dress covers the shoulders with a white flower, and the chest and belly are hidden under a
pink fabric, skirt resembles like is bud and each edge has pointed, translucent pink fabric
covers her head, purple eyes, blue hair, upper body close to the camera, occupying the
foreground', 'negative_prompt': 'happy expression, clean clothes, simple background, low
quality, blurry, distorted anatomy, FastNegativeV2, easynegative, verybadimagenegative_v1.3',
'guidance_scale': 6, 'generator': None, 'callback_on_step_end': <function diffusers_callback at
0x000001EB5E689620>, 'callback_on_step_end_tensor_inputs': ['latents', 'prompt_embeds',
'negative_prompt_embeds', 'add_text_embeds', 'add_time_ids', 'negative_pooled_prompt_embeds',
'negative_add_time_ids'], 'num_inference_steps': 20, 'eta': 1.0, 'guidance_rescale': 0,
'denoising_end': None, 'num_frames': 16, 'output_type': 'np'} Expected 3D (unbatched) or 4D
(batched) input to conv2d, but got input of size: [2, 4, 16, 128, 128]
23:54:09-496079 ERROR Processing: RuntimeError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│C:\ai\sdnext\modules\processing_diffusers.py:180 in process_base │
│ │
│ 179 │ │ │ taskid = shared.state.begin('Inference') │
│❱ 180 │ │ │ output = shared.sd_model(**base_args) │
│ 181 │ │ │ shared.state.end(taskid) │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils\_contextlib.py:116 in decorate_ │
│ │
│ 115 │ │ with ctx_factory(): │
│❱ 116 │ │ │ return func(*args, **kwargs) │
│ 117 │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\pipelines\animatediff\pipeline_an │
│ │
│ 1239 │ │ │ │ │ │
│❱ 1240 │ │ │ │ │ noise_pred = self.unet( │
│ 1241 │ │ │ │ │ │ latent_model_input, │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py:1739 in _wrapped │
│ │
│ 1738 │ │ else: │
│❱ 1739 │ │ │ return self._call_impl(*args, **kwargs) │
│ 1740 │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py:1750 in _call_im │
│ │
│ 1749 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │
│❱ 1750 │ │ │ return forward_call(*args, **kwargs) │
│ 1751 │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\_dynamo\eval_frame.py:574 in _fn │
│ │
│ 573 │ │ │ try: │
│❱ 574 │ │ │ │ return fn(*args, **kwargs) │
│ 575 │ │ │ finally: │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py:1739 in _wrapped │
│ │
│ 1738 │ │ else: │
│❱ 1739 │ │ │ return self._call_impl(*args, **kwargs) │
│ 1740 │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py:1750 in _call_im │
│ │
│ 1749 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │
│❱ 1750 │ │ │ return forward_call(*args, **kwargs) │
│ 1751 │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\models\unets\unet_2d_condition.py │
│ │
│ 1167 │ │ # 2. pre-process │
│❱ 1168 │ │ sample = self.conv_in(sample) │
│ 1169 │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py:1739 in _wrapped │
│ │
│ 1738 │ │ else: │
│❱ 1739 │ │ │ return self._call_impl(*args, **kwargs) │
│ 1740 │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py:1750 in _call_im │
│ │
│ 1749 │ │ │ │ or _global_forward_hooks or _global_forward_pre_hooks): │
│❱ 1750 │ │ │ return forward_call(*args, **kwargs) │
│ 1751 │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\conv.py:554 in forward │
│ │
│ 553 │ def forward(self, input: Tensor) -> Tensor: │
│❱ 554 │ │ return self._conv_forward(input, self.weight, self.bias) │
│ 555 │
│ │
│C:\Users\winbbs\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\conv.py:549 in _conv_forwa │
│ │
│ 548 │ │ │ ) │
│❱ 549 │ │ return F.conv2d( │
│ 550 │ │ │ input, weight, bias, self.stride, self.padding, self.dilation, self.groups │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
RuntimeError: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [2, 4, 16, 128, 128]
23:54:09-912135 DEBUG Search model: name="AnythingXL_xl [8421598e93]"
matched="C:\ai\sdnext\models\Stable-diffusion\AnythingXL_xl.safetensors" type=alias
23:54:09-929138 DEBUG Analyzed: model="AnythingXL_xl" type=AnimateDiffSDXLPipeline class=AnimateDiffSDXLPipeline
size=6938041578 mtime="2025-07-03 23:36:51" modules=[name="vae" cls=AutoencoderKL config=True
device=cpu dtype=torch.float32 params=83653863 modules=243, name="text_encoder"
cls=CLIPTextModel config=True device=cpu dtype=torch.float32 params=123060480 modules=152,
name="text_encoder_2" cls=CLIPTextModelWithProjection config=True device=cpu
dtype=torch.float32 params=694659840 modules=393, name="tokenizer" cls=CLIPTokenizer
config=False, name="tokenizer_2" cls=CLIPTokenizer config=False, name="unet"
cls=OptimizedModule config=True device=cpu dtype=torch.float32 params=2567463684 modules=1931,
name="motion_adapter" cls=MotionAdapter config=True device=cpu dtype=torch.float32
params=236779200 modules=465, name="scheduler" cls=EulerAncestralDiscreteScheduler config=True,
name="image_encoder" cls=NoneType config=False, name="feature_extractor" cls=NoneType
config=False, name="force_zeros_for_empty_prompt" cls=bool config=False]
23:54:09-931293 INFO Processing modifiers: unapply
23:54:09-939296 DEBUG Process: batch=1/1 interrupted
23:54:09-943800 INFO Processed: images=0 its=0.00 ops=['img2img', 'control', 'video']
23:54:09-944806 DEBUG Processed: timers={'total': 3.07, 'post': 2.95}
23:54:09-945803 DEBUG Processed: memory={'ram': {'total': 30.52, 'rss': 13.6, 'used': 25.57, 'free': 4.95, 'avail':
4.95, 'buffers': 0, 'cached': 0}, 'gpu': {'total': 0, 'used': 0, 'error': 'Torch not compiled
with CUDA enabled', 'swap': 0}, 'job': ''}
23:54:09-947056 DEBUG AnimateDiff video: type=MP4/MP4V duration=2 loop=True pad=1 interpolate=0Backend
Diffusers
Compute
OpenVINO
Interface
Standard
Branch
Dev
Model
StableDiffusion 1.5/2.1/XL
Acknowledgements
- I have read the above and searched for existing issues
- I confirm that this is classified correctly and its not an extension issue