Open SeBL4RD opened 1 year ago
t2i seems to be different from the most popular ControlNet. I never used that, does it have any significant advantages? If not I won't spend time to fix this.
Yes, it's very useful, it gives an inspiration simply based on an image, without prompting an image generation. It can be mixed with a Depth or other, and precisely mixed with other layers and prompt, it has an incredible impact. I'd understand if you didn't want to waste time with that. A little example : -A prompt with a BMW in a city -A autumn forest as inspiration
I just did another test, Clip_Vision and t2i_style work if the image is 512x512 (With MultiDIffusion), but if I go above with 768x768, I get the error mentioned above. Even if I greatly reduce the decoder tile size. Without MultiDiffusion, I can generate at these resolutions with these ControlNet layers.
Well I have just updated the readme, and currently start to investigate this. But first, I need to play with the t2i, which seems to be interesting. Would you please give me a link to that model?
https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/models/t2iadapter_style_sd14v1.pth
Use Clip_Vision as "Preprocessor" and this model.
Thank you. Let me play with it first :)
Sorry to come back to this, as we have a conversation here. It seems to have the same problem as last night with OpenPose, I have this crash again, while I use the same settings as last night, it's a bit off topic to post this here but here is the error when I activate OpenPose:
Arguments: ('task(wumsce6arqxcw4u)', 'Jacques Chirac, <lora:ChiracLora:1>, in a superman suit, flying on top of a city, majestic, trending on ArtStation, trending on CGSociety, Intricate, High Detail, Sharp focus, serenity, photorealistic photography art by midjourney and greg rutkowski\n', 'cartoon, 3d, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), wierd colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), out of frame, extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blur, bad art, bad anatomy, 3d render, freckles, watermark, text, url, hat, sunglasses, glasses', [], 50, 0, False, False, 1, 1, 13, 1259012780.0, -1.0, 0, 0, 0, False, 512, 910, True, 0.2, 2.35, 'ESRGAN 4x', 50, 0, 0, ['Model hash: c35782bad8'], 0, True, 'MultiDiffusion', False, True, 1024, 1024, 96, 96, 48, 4, 'None', 2, False, False, False, False, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, True, True, True, True, 0, 1536, 112, False, '', 0, False, False, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, None, 'Refresh models', <scripts.external_code.ControlNetUnit object at 0x00000206764D7010>, <scripts.external_code.ControlNetUnit object at 0x000002067525FFD0>, <scripts.external_code.ControlNetUnit object at 0x000002067525FA60>, False, '1:1,1:2,1:2', '0:0,0:0,0:1', '0.2,0.8,0.8', 20, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0, None, False, None, False, None, False, 50) {}
Traceback (most recent call last):
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\txt2img.py", line 56, in txt2img
processed = process_images(p)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\processing.py", line 486, in process_images
res = process_images_inner(p)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\processing.py", line 636, 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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\processing.py", line 924, in sample
samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 324, in sample_img2img
samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 227, in launch_sampling
return func()
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 324, in <lambda>
samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 138, in forward
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": c_crossattn, "c_concat": [image_cond_in[a:b]]})
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\multidiffusion-upscaler-for-automatic1111\utils\utils.py", line 179, in wrapper
return fn(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\multidiffusion-upscaler-for-automatic1111\methods\multidiffusion.py", line 104, in kdiff_forward
return self.sample_one_step(x_in, org_func, repeat_func, custom_func)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\multidiffusion-upscaler-for-automatic1111\methods\multidiffusion.py", line 157, in sample_one_step
return org_func(x_in)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\multidiffusion-upscaler-for-automatic1111\methods\multidiffusion.py", line 90, in org_func
return self.sampler_forward(x, sigma_in, cond=cond)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 138, in get_eps
return self.inner_model.apply_model(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\sd_hijack_utils.py", line 28, in __call__
return self.__orig_func(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1212, in _call_impl
result = forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 233, in forward2
return forward(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\cldm.py", line 115, in forward
return self.control_model(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\cldm.py", line 380, in forward
h += guided_hint
RuntimeError: output with shape [1, 320, 150, 267] doesn't match the broadcast shape [2, 320, 150, 267]
Generation works to 50%, and when HiresFix start, Crash with this message, yesterday night, was generating in 2100x1200 with Openpose, was working well :
I know what happened. I will fix it in 10 min.
Please have a try now.
Error completing request
Arguments: ('task(p28p0shv7xq1f6l)', 'Jacques Chirac, <lora:ChiracLora:1>, in a superman suit, flying on top of a city, majestic, trending on ArtStation, trending on CGSociety, Intricate, High Detail, Sharp focus, serenity, photorealistic photography art by midjourney and greg rutkowski\n', 'cartoon, 3d, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), wierd colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), out of frame, extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blur, bad art, bad anatomy, 3d render, freckles, watermark, text, url, hat, sunglasses, glasses', [], 50, 0, False, False, 1, 1, 13, 1259012780.0, -1.0, 0, 0, 0, False, 512, 910, True, 0.2, 2.35, 'ESRGAN 4x', 50, 0, 0, ['Model hash: c35782bad8'], 0, True, 'MultiDiffusion', False, True, 1024, 1024, 96, 96, 48, 4, 'None', 2, False, False, False, False, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, True, True, True, True, 0, 1536, 160, False, '', 0, False, False, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, 'LoRA', 'None', 0, 0, None, 'Refresh models', <scripts.external_code.ControlNetUnit object at 0x00000254770BD420>, <scripts.external_code.ControlNetUnit object at 0x0000025476E96230>, <scripts.external_code.ControlNetUnit object at 0x0000025476E955D0>, False, '1:1,1:2,1:2', '0:0,0:0,0:1', '0.2,0.8,0.8', 20, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0, None, False, None, False, None, False, 50) {}
Traceback (most recent call last):
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\txt2img.py", line 56, in txt2img
processed = process_images(p)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\processing.py", line 486, in process_images
res = process_images_inner(p)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\processing.py", line 636, 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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\processing.py", line 924, in sample
samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 324, in sample_img2img
samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 227, in launch_sampling
return func()
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 324, in <lambda>
samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 138, in forward
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": c_crossattn, "c_concat": [image_cond_in[a:b]]})
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\multidiffusion-upscaler-for-automatic1111\utils\utils.py", line 179, in wrapper
return fn(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\multidiffusion-upscaler-for-automatic1111\methods\multidiffusion.py", line 104, in kdiff_forward
return self.sample_one_step(x_in, org_func, repeat_func, custom_func)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\multidiffusion-upscaler-for-automatic1111\methods\multidiffusion.py", line 157, in sample_one_step
self.reset_controlnet_tensors()
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\multidiffusion-upscaler-for-automatic1111\methods\multidiffusion.py", line 90, in org_func
return self.sampler_forward(x, sigma_in, cond=cond)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 138, in get_eps
return self.inner_model.apply_model(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\modules\sd_hijack_utils.py", line 28, in __call__
return self.__orig_func(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1212, in _call_impl
result = forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 233, in forward2
return forward(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\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 "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\cldm.py", line 115, in forward
return self.control_model(*args, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\Seb\Desktop\Stable Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\cldm.py", line 380, in forward
h += guided_hint
RuntimeError: output with shape [1, 320, 150, 267] doesn't match the broadcast shape [2, 320, 150, 267]
Forget my previous comment, its working. Restarted SD after extension updates solved the problem
No crash at the moment, 60%
OpenPose works back in Hires.Fix, thank you :)
OK now?
Well, fantastic work.
Well, fantastic work.
Its supposed to be "Super Menteur", A humorous character by Jacques Chirac, in the 90s-00s
So? you were able to do what you wanted with t2i_Style?
I now have no time to continue. Will do it in spare time.
Ok :)
If you have discord, it may be easier to report to you: SeBL4RD#6090
Did a rollback to b1bc3339c1c6c5447f53d34c0413417215ca4d81
It was broken again with OpenPose
Error when ControlNet Clip_Vision Preprocessing (t2i_adaptater_style_sd14v1) is enabled. Generation just crash.