Open richardlampitt opened 10 months ago
Hello,
I've been trying to get ControlNet to function in A1111, but regardless of what I'm trying to do it always returns this error:
2024-01-23 22:40:49,817 - ControlNet - INFO - unit_separate = False, style_align = False 2024-01-23 22:40:50,253 - ControlNet - INFO - Loading model: control_sd15_openpose [fef5e48e] *** Error running process: D:\ai\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\controlnet.py Traceback (most recent call last): File "D:\ai\stable-diffusion-webui\modules\scripts.py", line 718, in process script.process(p, *script_args) File "D:\ai\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 1117, in process self.controlnet_hack(p) File "D:\ai\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 1102, in controlnet_hack self.controlnet_main_entry(p) File "D:\ai\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 882, in controlnet_main_entry model_net, control_model_type = Script.load_control_model(p, unet, unit.model) File "D:\ai\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 343, in load_control_model control_model = Script.build_control_model(p, unet, model) File "D:\ai\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 371, in build_control_model state_dict = load_state_dict(model_path) File "D:\ai\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\utils.py", line 21, in load_state_dict state_dict = unsafe_torch_load(ckpt_path, map_location=torch.device(location)) File "D:\ai\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 712, in load return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args) File "D:\ai\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 1049, in _load result = unpickler.load() File "D:\Program Files\Python310\lib\pickle.py", line 1213, in load dispatch[key[0]](self) File "D:\Program Files\Python310\lib\pickle.py", line 1254, in load_binpersid self.append(self.persistent_load(pid)) File "D:\ai\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 1019, in persistent_load load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location)) File "D:\ai\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 997, in load_tensor storage = zip_file.get_storage_from_record(name, numel, torch._UntypedStorage).storage()._untyped() RuntimeError: PytorchStreamReader failed reading file data/25: invalid header or archive is corrupted
I've already updated A1111 to 1.7.0, and I have uninstalled and reinstalled ControlNet twice, but still no luck.
Please advise.
For those coming from search engines and/or ChatGPT - I finally managed to get ControlNet working using the control_v11p_sd15_openpose.pht model.
control_v11p_sd15_openpose.pht
Hello,
I've been trying to get ControlNet to function in A1111, but regardless of what I'm trying to do it always returns this error:
I've already updated A1111 to 1.7.0, and I have uninstalled and reinstalled ControlNet twice, but still no luck.
Please advise.