Closed enzyme69 closed 1 year ago
Does the hash matter in the model name? [fef5e48e] is mine. I did not type it on the hardcode python script.
When the txt2img does nothing, I use img2img and getting error:
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 407, in run_asgi
result = await app( # type: ignore[func-returns-value]
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 78, in __call__
return await self.app(scope, receive, send)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/fastapi/applications.py", line 271, in __call__
await super().__call__(scope, receive, send)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/starlette/applications.py", line 125, in __call__
await self.middleware_stack(scope, receive, send)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/starlette/middleware/errors.py", line 184, in __call__
raise exc
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/starlette/middleware/errors.py", line 162, in __call__
await self.app(scope, receive, _send)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/starlette/middleware/gzip.py", line 24, in __call__
await responder(scope, receive, send)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/starlette/middleware/gzip.py", line 44, in __call__
await self.app(scope, receive, self.send_with_gzip)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 79, in __call__
raise exc
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 68, in __call__
await self.app(scope, receive, sender)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 21, in __call__
raise e
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 18, in __call__
await self.app(scope, receive, send)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/starlette/routing.py", line 706, in __call__
await route.handle(scope, receive, send)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/starlette/routing.py", line 276, in handle
await self.app(scope, receive, send)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/starlette/routing.py", line 66, in app
response = await func(request)
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/fastapi/routing.py", line 237, in app
raw_response = await run_endpoint_function(
File "/Users/jimmygunawan/stable-diffusion-webui/venv/lib/python3.10/site-packages/fastapi/routing.py", line 163, in run_endpoint_function
return await dependant.call(**values)
File "/Users/jimmygunawan/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/api.py", line 321, in img2img
processed = process_images(p)
File "/Users/jimmygunawan/stable-diffusion-webui/modules/processing.py", line 486, in process_images
res = process_images_inner(p)
File "/Users/jimmygunawan/stable-diffusion-webui/modules/processing.py", line 577, in process_images_inner
p.init(p.all_prompts, p.all_seeds, p.all_subseeds)
File "/Users/jimmygunawan/stable-diffusion-webui/modules/processing.py", line 1015, in init
image = image.to(shared.device)
File "/Users/jimmygunawan/stable-diffusion-webui/modules/sd_hijack_utils.py", line 17, in <lambda>
setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
File "/Users/jimmygunawan/stable-diffusion-webui/modules/sd_hijack_utils.py", line 26, in __call__
return self.__sub_func(self.__orig_func, *args, **kwargs)
File "/Users/jimmygunawan/stable-diffusion-webui/modules/mac_specific.py", line 39, in <lambda>
CondFunc('torch.Tensor.to', lambda orig_func, self, *args, **kwargs: orig_func(self.contiguous(), *args, **kwargs),
TypeError: Cannot convert a MPS Tensor to float64 dtype as the MPS framework doesn't support float64. Please use float32 instead.
My suspicion is that your script does not enable this button? So my result has not been using the ControlNet.
I'm facing the same problem after updating Mikubill/sd-webui-controlnet to latest version last night. Tried rollbacking to previous commit, eg: f94b453d10c2eb4e3ad57b7cdfdd17e60a557b3e fix it.
Does the hash matter in the model name? [fef5e48e] is mine. I did not type it on the hardcode python script.
Yes, hash matters. You can get the whole cn models list here: http://localhost:7860/docs#/default/model_list_controlnet_model_list_get
Maybe related: Mikubill/sd-webui-controlnet#194 (comment)
Thx, didn't know that.
This time no error message.... however I tried many times and just realized I am not really getting any relationship between Blender original render and the processed via webUI ControlNet. My code might be wrong.
It's almost like the check is turned off when I send the command from Blender via F12. I did get the render before after:
Only if I use the same image render output and do it manually on webUI, it works.