sd-webui-controlnet
sd-webui-controlnet copied to clipboard
Published
20 hours ago •
Mikubill
Mikubill
[Bug]:
Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui
What happened?
using Clip_Vision with the t2iadapter_sketch returns an error: RuntimeError: Tensors must have same number of dimensions: got 4 and 3
Steps to reproduce the problem
- Go to text2img
- add contolnet with clip_vision and t2iadapter_sketch
- generate
error
What should have happened?
it should generate image
Commit where the problem happens
webui: 3c922d983bf60ba187b5422b3690e6b7fb07777e controlnet: 4c13542c (Sun Mar 12 11:14:08 2023)
What browsers do you use to access the UI ?
No response
Command Line Arguments
--xformers
Console logs
Loading model from cache: t2iadapter_style_sd14v1 [202e85cc]
Loading preprocessor: none
0%| | 0/20 [00:00<?, ?it/s]
Error completing request
Arguments: ('task(4cyxqkvw6ey6fmn)', 'Redhead, beautiful, woman, spy, agent, modern disney style', 'background, out of frame, duplicate, watermark, signature, text, ugly, morbid, mutated, deformed, blurry, bad anatomy, bad proportions, cloned face, disfigured, fused fingers, fused limbs, too many fingers, long neck, ', [], 20, 0, True, False, 1, 1, 7, 1385296670.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, True, False, 0, -1, False, False, 1024, 1024, True, 64, 64, 32, 1, 'None', 2, False, False, False, True, True, 0, 960, 64, False, '', 0, False, True, True, 'canny', 'control_canny-fp16 [e3fe7712]', 1, {'image': array([[[255, 255, 255],
[255, 255, 255],
[255, 255, 255],
...,
[255, 255, 255],
[255, 255, 255],
[255, 255, 255]],
[[255, 255, 255],
[255, 255, 255],
[255, 255, 255],
...,
[255, 255, 255],
[255, 255, 255],
[255, 255, 255]],
[[255, 255, 255],
[255, 255, 255],
[255, 255, 255],
...,
[255, 255, 255],
[255, 255, 255],
[255, 255, 255]],
...,
[[255, 255, 255],
[255, 255, 255],
[255, 255, 255],
...,
[255, 255, 255],
[255, 255, 255],
[255, 255, 255]],
[[255, 255, 255],
[255, 255, 255],
[255, 255, 255],
...,
[255, 255, 255],
[255, 255, 255],
[255, 255, 255]],
[[255, 255, 255],
[255, 255, 255],
[255, 255, 255],
...,
[255, 255, 255],
[255, 255, 255],
[255, 255, 255]]], dtype=uint8), 'mask': array([[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
...,
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]]], dtype=uint8)}, False, 'Scale to Fit (Inner Fit)', False, False, 512, 100, 200, 0, 1, False, True, 'none', 't2iadapter_style_sd14v1 [202e85cc]', 1, {'image': array([[[ 85, 69, 75],
[ 83, 69, 76],
[ 83, 68, 75],
...,
[106, 94, 104],
[106, 95, 106],
[104, 94, 104]],
[[ 86, 70, 77],
[ 84, 69, 75],
[ 84, 70, 76],
...,
[106, 95, 105],
[105, 95, 106],
[105, 95, 106]],
[[ 86, 69, 76],
[ 84, 70, 75],
[ 84, 70, 76],
...,
[106, 95, 105],
[106, 95, 104],
[106, 94, 105]],
...,
[[153, 149, 171],
[153, 150, 171],
[150, 147, 168],
...,
[184, 182, 206],
[183, 180, 205],
[184, 182, 206]],
[[152, 151, 172],
[153, 152, 172],
[153, 149, 170],
...,
[185, 184, 207],
[183, 180, 206],
[186, 185, 210]],
[[155, 153, 172],
[150, 148, 170],
[153, 148, 172],
...,
[182, 178, 204],
[184, 183, 206],
[190, 190, 209]]], dtype=uint8), 'mask': array([[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
...,
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]]], dtype=uint8)}, False, 'Envelope (Outer Fit)', False, True, 64, 64, 64, 0, 1, False, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0, '', 5, 24, 12.5, 1000, '', 'DDIM', 0, 64, 64, '', 64, 7.5, 0.42, 'DDIM', 64, 64, 1, 0, 92, True, True, True, False, False, False, 'midas_v21_small', None, None, 50, 0, 0, 512, 512, False, False, True, True, True, False, False, 1, False, False, 2.5, 4, 0, False, 0, 1, False, False, 'u2net', False, False, False, False) {}
Traceback (most recent call last):
File "G:\stable-diffusion-webui\modules\call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "G:\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "G:\stable-diffusion-webui\modules\txt2img.py", line 56, in txt2img
processed = process_images(p)
File "G:\stable-diffusion-webui\modules\processing.py", line 486, in process_images
res = process_images_inner(p)
File "G:\stable-diffusion-webui\modules\processing.py", line 635, in process_images_inner
samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
File "G:\stable-diffusion-webui\modules\processing.py", line 835, in sample
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
File "G:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 351, in sample
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
File "G:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 227, in launch_sampling
return func()
File "G:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 351, in <lambda>
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "G:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\sampling.py", line 145, in sample_euler_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 119, in forward
x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 112, in forward
eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
File "G:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 138, in get_eps
return self.inner_model.apply_model(*args, **kwargs)
File "G:\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 "G:\stable-diffusion-webui\modules\sd_hijack_utils.py", line 28, in __call__
return self.__orig_func(*args, **kwargs)
File "G:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 858, in apply_model
x_recon = self.model(x_noisy, t, **cond)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 1329, in forward
out = self.diffusion_model(x, t, context=cc)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 233, in forward2
return forward(*args, **kwargs)
File "G:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 130, in forward
control = param.control_model(x=x, hint=param.hint_cond, timesteps=timesteps, context=context)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\adapter.py", line 105, in forward
self.control = self.control_model(hint_in)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\adapter.py", line 325, in forward
x = torch.cat([x, style_embedding], dim=1)
RuntimeError: Tensors must have same number of dimensions: got 4 and 3
another attempt:
Loading preprocessor: clip_vision
0%| | 0/20 [00:00<?, ?it/s]
Error completing request
Arguments: ('task(vdjhn63rxvca669)', 'Redhead, beautiful, woman, spy, agent, modern disney style', 'background, out of frame, duplicate, watermark, signature, text, ugly, morbid, mutated, deformed, blurry, bad anatomy, bad proportions, cloned face, disfigured, fused fingers, fused limbs, too many fingers, long neck,', [], 20, 0, True, False, 1, 1, 7, 1385296670.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, True, False, 0, -1, False, False, 1024, 1024, True, 64, 64, 32, 1, 'None', 2, False, False, False, True, True, 0, 960, 64, False, '', 0, False, True, True, 'clip_vision', 't2iadapter_sketch-fp16 [75b15924]', 1, {'image': array([[[ 85, 69, 75],
[ 83, 69, 76],
[ 83, 68, 75],
...,
[106, 94, 104],
[106, 95, 106],
[104, 94, 104]],
[[ 86, 70, 77],
[ 84, 69, 75],
[ 84, 70, 76],
...,
[106, 95, 105],
[105, 95, 106],
[105, 95, 106]],
[[ 86, 69, 76],
[ 84, 70, 75],
[ 84, 70, 76],
...,
[106, 95, 105],
[106, 95, 104],
[106, 94, 105]],
...,
[[153, 149, 171],
[153, 150, 171],
[150, 147, 168],
...,
[184, 182, 206],
[183, 180, 205],
[184, 182, 206]],
[[152, 151, 172],
[153, 152, 172],
[153, 149, 170],
...,
[185, 184, 207],
[183, 180, 206],
[186, 185, 210]],
[[155, 153, 172],
[150, 148, 170],
[153, 148, 172],
...,
[182, 178, 204],
[184, 183, 206],
[190, 190, 209]]], dtype=uint8), 'mask': array([[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
...,
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]],
[[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
...,
[ 0, 0, 0, 255],
[ 0, 0, 0, 255],
[ 0, 0, 0, 255]]], dtype=uint8)}, False, 'Scale to Fit (Inner Fit)', False, False, 512, 64, 64, 0, 1, False, False, 'none', 'None', 1, None, False, 'Scale to Fit (Inner Fit)', False, False, 64, 64, 64, 0, 1, False, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0, '', 5, 24, 12.5, 1000, '', 'DDIM', 0, 64, 64, '', 64, 7.5, 0.42, 'DDIM', 64, 64, 1, 0, 92, True, True, True, False, False, False, 'midas_v21_small', None, None, 50, 0, 0, 512, 512, False, False, True, True, True, False, False, 1, False, False, 2.5, 4, 0, False, 0, 1, False, False, 'u2net', False, False, False, False) {}
Traceback (most recent call last):
File "G:\stable-diffusion-webui\modules\call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "G:\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "G:\stable-diffusion-webui\modules\txt2img.py", line 56, in txt2img
processed = process_images(p)
File "G:\stable-diffusion-webui\modules\processing.py", line 486, in process_images
res = process_images_inner(p)
File "G:\stable-diffusion-webui\modules\processing.py", line 635, in process_images_inner
samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
File "G:\stable-diffusion-webui\modules\processing.py", line 835, in sample
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
File "G:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 351, in sample
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
File "G:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 227, in launch_sampling
return func()
File "G:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 351, in <lambda>
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "G:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\sampling.py", line 145, in sample_euler_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 119, in forward
x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 112, in forward
eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
File "G:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 138, in get_eps
return self.inner_model.apply_model(*args, **kwargs)
File "G:\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 "G:\stable-diffusion-webui\modules\sd_hijack_utils.py", line 28, in __call__
return self.__orig_func(*args, **kwargs)
File "G:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 858, in apply_model
x_recon = self.model(x_noisy, t, **cond)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 1329, in forward
out = self.diffusion_model(x, t, context=cc)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 233, in forward2
return forward(*args, **kwargs)
File "G:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 176, in forward
control = param.control_model(x=x_in, hint=param.hint_cond, timesteps=timesteps, context=context)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\adapter.py", line 105, in forward
self.control = self.control_model(hint_in)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "G:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\adapter.py", line 257, in forward
x = self.unshuffle(x)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "g:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\pixelshuffle.py", line 104, in forward
return F.pixel_unshuffle(input, self.downscale_factor)
RuntimeError: pixel_unshuffle expects height to be divisible by downscale_factor, but input.size(-2)=1 is not divisible by 8
Additional information
No response
