NameError: name 'CLIPVisionModelWithProjection' is not defined

[nikolaiusa]

model 2.2 i did not upload - Should the download start automatically? After setup and restart SD:

Starting Prior Error completing request Arguments: ('task(640qqqw29a93lvf)', '', '', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 0, '', '', [], 4, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, None, 64, 4, '2.2', 0.5, 0.5, True) {} Traceback (most recent call last): File "I:\stable-diffusion-webui-1.3.2\modules\call_queue.py", line 57, in f res = list(func(*args, *kwargs)) File "I:\stable-diffusion-webui-1.3.2\modules\call_queue.py", line 37, in f res = func(args, *kwargs) File "I:\stable-diffusion-webui-1.3.2\modules\txt2img.py", line 54, in txt2img processed = modules.scripts.scripts_txt2img.run(p, args) File "I:\stable-diffusion-webui-1.3.2\modules\scripts.py", line 441, in run processed = script.run(p, *script_args) File "I:\stable-diffusion-webui-1.3.2\extensions\kandinsky-for-automatic1111\scripts\kandinsky_script.py", line 107, in run return shared.kandinsky_model.process_images(p) File "I:\stable-diffusion-webui-1.3.2\extensions/kandinsky-for-automatic1111/scripts\abstract_model.py", line 260, in process_images self.load_encoder() File "I:\stable-diffusion-webui-1.3.2\extensions/kandinsky-for-automatic1111/scripts\kandinsky.py", line 80, in load_encoder self.image_encoder = CLIPVisionModelWithProjection.from_pretrained( NameError: name 'CLIPVisionModelWithProjection' is not defined

[nikolaiusa]

i changed the version and it worked

Successfully uninstalled diffusers-0.17.1 Successfully installed diffusers-0.20.0

[nikolaiusa]

but in 2.1 error)

Error completing request Arguments: ('task(lpu1km615n9j5e1)', 'cat', '', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 0, '', '', [], 4, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, None, 64, 4, '2.1', 0.5, 0.5, False) {} Traceback (most recent call last): File "I:\stable-diffusion-webui-1.3.2\extensions/kandinsky-for-automatic1111/scripts\abstract_model.py", line 398, in process_images self.main_model_to_cpu() File "I:\stable-diffusion-webui-1.3.2\extensions/kandinsky-for-automatic1111/scripts\kandinsky.py", line 166, in main_model_to_cpu self.pipe.to("cpu") File "I:\stable-diffusion-webui-1.3.2\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 727, in to module.to(torch_device, torch_dtype) File "I:\stable-diffusion-webui-1.3.2\venv\lib\site-packages\torch\nn\modules\module.py", line 1145, in to return self._apply(convert) File "I:\stable-diffusion-webui-1.3.2\venv\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply module._apply(fn) File "I:\stable-diffusion-webui-1.3.2\venv\lib\site-packages\torch\nn\modules\module.py", line 820, in _apply param_applied = fn(param) File "I:\stable-diffusion-webui-1.3.2\venv\lib\site-packages\torch\nn\modules\module.py", line 1143, in convert return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking) NotImplementedError: Cannot copy out of meta tensor; no data!

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "I:\stable-diffusion-webui-1.3.2\modules\call_queue.py", line 57, in f res = list(func(*args, *kwargs)) File "I:\stable-diffusion-webui-1.3.2\modules\call_queue.py", line 37, in f res = func(args, *kwargs) File "I:\stable-diffusion-webui-1.3.2\modules\txt2img.py", line 54, in txt2img processed = modules.scripts.scripts_txt2img.run(p, args) File "I:\stable-diffusion-webui-1.3.2\modules\scripts.py", line 441, in run processed = script.run(p, *script_args) File "I:\stable-diffusion-webui-1.3.2\extensions\kandinsky-for-automatic1111\scripts\kandinsky_script.py", line 107, in run return shared.kandinsky_model.process_images(p) File "I:\stable-diffusion-webui-1.3.2\extensions/kandinsky-for-automatic1111/scripts\abstract_model.py", line 438, in process_images self.cleanup_on_error() File "I:\stable-diffusion-webui-1.3.2\extensions/kandinsky-for-automatic1111/scripts\kandinsky.py", line 220, in cleanup_on_error self.main_model_to_cpu() File "I:\stable-diffusion-webui-1.3.2\extensions/kandinsky-for-automatic1111/scripts\kandinsky.py", line 166, in main_model_to_cpu self.pipe.to("cpu") File "I:\stable-diffusion-webui-1.3.2\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 727, in to module.to(torch_device, torch_dtype) File "I:\stable-diffusion-webui-1.3.2\venv\lib\site-packages\torch\nn\modules\module.py", line 1145, in to return self._apply(convert) File "I:\stable-diffusion-webui-1.3.2\venv\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply module._apply(fn) File "I:\stable-diffusion-webui-1.3.2\venv\lib\site-packages\torch\nn\modules\module.py", line 820, in _apply param_applied = fn(param) File "I:\stable-diffusion-webui-1.3.2\venv\lib\site-packages\torch\nn\modules\module.py", line 1143, in convert return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking) NotImplementedError: Cannot copy out of meta tensor; no data!

[nikolaiusa]

I:\stable-diffusion-webui-1.3.2\extensions\kandinsky-for-automatic1111\scripts\kandinsky.py i changed line 21 and 2.1 worked

21 move_to_cuda=True

[nikolaiusa]

and another question - what needs to be changed to use Kandinsky offline?

requests.exceptions.ConnectionError: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/kandinsky-community/kandinsky-2-1-prior (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x00000211B78E0CA0>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed'))"), '(Request ID: 17cfaf22-a980-47c0-983c-75d343d72d65)')