psychedelicious
commented
1 month ago This error typically means the model didn't download fully. Try disabling it and re-downloading it.
Open z0rge opened 1 month ago
psychedelicious
commented
1 month ago This error typically means the model didn't download fully. Try disabling it and re-downloading it.
Is there an existing issue for this problem?
Operating system
Windows
GPU vendor
Nvidia (CUDA)
GPU model
RTX4090 i9
GPU VRAM
64GB
Version number
5.2.0
Browser
Opera one 114.0.5282.102, Pinokio 2.15.1(with xformers)
Python dependencies
{ "accelerate": "0.30.1", "compel": "2.0.2", "cuda": "12.4", "diffusers": "0.27.2", "numpy": "1.26.4", "opencv": "4.9.0.80", "onnx": "1.16.1", "pillow": "11.0.0", "python": "3.10.6", "torch": "2.4.1+cu124", "torchvision": "0.19.1+cu124", "transformers": "4.41.1", "xformers": null }
What happened
Flux Union Controlnet doesn't work and give that in console [2024-10-21 18:32:27,967]::[InvokeAI]::ERROR --> Error while invoking session 0e026243-71a7-43be-9278-277eaed20c77, invocation 22120cc4-761a-4785-a870-06903a6fcc90 (flux_denoise): Error while deserializing header: MetadataIncompleteBuffer [2024-10-21 18:32:27,967]::[InvokeAI]::ERROR --> Traceback (most recent call last): File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\app\services\session_processor\session_processor_default.py", line 129, in run_node output = invocation.invoke_internal(context=context, services=self._services) File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\app\invocations\baseinvocation.py", line 290, in invoke_internal output = self.invoke(context) File "D:_AI\Invokeai.venv\lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\app\invocations\flux_denoise.py", line 105, in invoke latents = self._run_diffusion(context) File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\app\invocations\flux_denoise.py", line 210, in _run_diffusion controlnet_extensions = self._prep_controlnet_extensions( File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\app\invocations\flux_denoise.py", line 338, in _prep_controlnet_extensions controlnet_models = [context.models.load(controlnet.control_model) for controlnet in controlnets] File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\app\invocations\flux_denoise.py", line 338, in
controlnet_models = [context.models.load(controlnet.control_model) for controlnet in controlnets]
File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\app\services\shared\invocation_context.py", line 370, in load
return self._services.model_manager.load.load_model(model, _submodel_type)
File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\app\services\model_load\model_load_default.py", line 70, in load_model
).load_model(model_config, submodel_type)
File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\backend\model_manager\load\load_default.py", line 56, in load_model
locker = self._load_and_cache(model_config, submodel_type)
File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\backend\model_manager\load\load_default.py", line 77, in _load_and_cache
loaded_model = self._load_model(config, submodel_type)
File "D:_AI\Invokeai.venv\lib\site-packages\invokeai\backend\model_manager\load\model_loaders\flux.py", line 327, in _load_model
sd = load_file(model_path)
File "D:_AI\Invokeai.venv\lib\site-packages\safetensors\torch.py", line 311, in load_file
with safe_open(filename, framework="pt", device=device) as f:
safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer
What you expected to happen
I expected that Flux controlnet will work)
How to reproduce the problem
choose Flux Dev(Quanisated) add raster image and Flux Union Controlnet
Additional context
No response
Discord username
No response