[Bug]: All Reference Preprocessors are generating errors for SD1.5 and SDXL models

[Shangooriginal]

Is there an existing issue for this?

• I have searched the existing issues and checked the recent builds/commits of both this extension and the webui

What happened?

All the Reference Preprocessors are generating errors when I try to use them either with SD1.5 and SDXL models.

Steps to reproduce the problem

I upload picture for reference and adjust the settings, click generate and error message appears. See below

RuntimeError: shape '[81920, 8, 40]' is invalid for input of size 3276800

What should have happened?

It should just work and generate a new reference image output

Commit where the problem happens

webui: version: [v1.7.0-RC-4-g120a84bd]
controlnet: [a13bd2f]

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

x-formers

List of enabled extensions

Non applicable

Console logs

RuntimeError: shape '[81920, 8, 40]' is invalid for input of size 3276800

*** Error completing request
*** Arguments: ('task(2bl0opahhbql4kh)', 'Fashion model, Asian ethnicity, futuristic urban wear, metallic accents, sleek lines, white background', '', ['Easy_Bad_NegPrompt'], 30, 'DPM++ 2M SDE Karras', 1, 1, 7, 640, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], <gradio.routes.Request object at 0x000001CA12ADA560>, 0, -1, False, -1, 0, 0, 0, False, '', 0.8, False, False, False, False, 'base', False, False, {'ad_model': 'face_yolov8n.pt', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'Euler a', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, {'ad_model': 'None', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'Euler a', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, False, 'MultiDiffusion', False, True, 1024, 1024, 96, 96, 48, 4, 'None', 2, False, 10, 1, 1, 64, False, False, False, False, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 3072, 192, True, True, True, False, False, 7, 100, 'Constant', 0, 'Constant', 0, 4, True, 'MEAN', 'AD', 1, UiControlNetUnit(enabled=True, module='reference_adain+attn', model='None', weight=1, image={'image': array([[[193, 193, 194],
***         [193, 193, 196],
***         [191, 192, 194],
***         ...,
***         [183, 184, 183],
***         [182, 184, 184],
***         [183, 182, 183]],
***
***        [[192, 191, 193],
***         [193, 193, 195],
***         [193, 191, 195],
***         ...,
***         [183, 183, 184],
***         [183, 183, 184],
***         [182, 182, 184]],
***
***        [[191, 190, 193],
***         [191, 192, 193],
***         [193, 193, 194],
***         ...,
***         [184, 184, 185],
***         [183, 184, 183],
***         [184, 182, 183]],
***
***        ...,
***
***        [[225, 224, 229],
***         [224, 223, 228],
***         [224, 224, 227],
***         ...,
***         [223, 225, 228],
***         [222, 224, 227],
***         [223, 223, 228]],
***
***        [[225, 225, 229],
***         [224, 224, 227],
***         [224, 224, 228],
***         ...,
***         [221, 223, 225],
***         [221, 222, 225],
***         [222, 223, 226]],
***
***        [[225, 224, 229],
***         [224, 224, 229],
***         [225, 223, 230],
***         ...,
***         [223, 223, 227],
***         [222, 224, 226],
***         [222, 222, 224]]], dtype=uint8), 'mask': array([[[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]],
***
***        [[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]],
***
***        [[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]],
***
***        ...,
***
***        [[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]],
***
***        [[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]],
***
***        [[0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0],
***         ...,
***         [0, 0, 0],
***         [0, 0, 0],
***         [0, 0, 0]]], dtype=uint8)}, resize_mode='Crop and Resize', low_vram=False, processor_res=-1, threshold_a=0.5, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=64, threshold_a=64, threshold_b=64, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=64, threshold_a=64, threshold_b=64, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=64, threshold_a=64, threshold_b=64, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), False, True, 3, 4, 0.15, 0.3, 'bicubic', 0.5, 2, True, False, False, False, 'Matrix', 'Columns', 'Mask', 'Prompt', '1,1', '0.2', False, False, False, 'Attention', [False], '0', '0', '0.4', None, '0', '0', False, None, False, '0', '0', 'inswapper_128.onnx', 'CodeFormer', 1, True, 'None', 1, 1, False, True, 1, 0, 0, False, 0.5, True, False, 'CUDA', False, 0, 'None', '', None, False, False, 0, None, [], 0, False, [], [], False, 0, 1, False, False, 0, None, [], -2, False, [], False, 0, None, None, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, False, None, None, False, None, None, False, None, None, False, None, None, False, 50, [], 30, '', 4, [], 1, '', '', '', '') {}
    Traceback (most recent call last):
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\call_queue.py", line 57, in f
        res = list(func(*args, **kwargs))
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\call_queue.py", line 36, in f
        res = func(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\txt2img.py", line 55, in txt2img
        processed = processing.process_images(p)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\processing.py", line 734, in process_images
        res = process_images_inner(p)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 42, in processing_process_images_hijack
        return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\processing.py", line 868, in process_images_inner
        samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 423, in process_sample
        return process.sample_before_CN_hack(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\processing.py", line 1142, in sample
        samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 235, in sample
        samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\sd_samplers_common.py", line 261, in launch_sampling
        return func()
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 235, in <lambda>
        samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
        return func(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\sampling.py", line 626, in sample_dpmpp_2m_sde
        denoised = model(x, sigmas[i] * s_in, **extra_args)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\sd_samplers_cfg_denoiser.py", line 169, in forward
        x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict(cond_in, image_cond_in))
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-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\xxxxx\Documents\WebUI-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\xxxxx\Documents\WebUI-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\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\sd_hijack_utils.py", line 28, in __call__
        return self.__orig_func(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-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\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 1335, in forward
        out = self.diffusion_model(x, t, context=cc)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 840, in forward_webui
        raise e
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 837, in forward_webui
        return forward(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 722, in forward
        outer.original_forward(
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\sd_unet.py", line 91, in UNetModel_forward
        return original_forward(self, x, timesteps, context, *args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 797, in forward
        h = module(h, emb, context)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 84, in forward
        x = layer(x, context)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 334, in forward
        x = block(x, context=context[i])
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 269, in forward
        return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\util.py", line 121, in checkpoint
        return CheckpointFunction.apply(func, len(inputs), *args)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\function.py", line 506, in apply
        return super().apply(*args, **kwargs)  # type: ignore[misc]
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\util.py", line 136, in forward
        output_tensors = ctx.run_function(*ctx.input_tensors)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 884, in hacked_basic_transformer_inner_forward
        self_attn1 = self.attn1(x_norm1, context=self_attention_context)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\extensions-builtin\hypertile\hypertile.py", line 307, in wrapper
        out = params.forward(x, *args[1:], **kwargs)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\modules\sd_hijack_optimizations.py", line 496, in xformers_attention_forward
        out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=get_xformers_flash_attention_op(q, k, v))
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 192, in memory_efficient_attention
        return _memory_efficient_attention(
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 290, in _memory_efficient_attention
        return _memory_efficient_attention_forward(
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 310, in _memory_efficient_attention_forward
        out, *_ = op.apply(inp, needs_gradient=False)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\xformers\ops\fmha\flash.py", line 235, in apply
        ) = _convert_input_format(inp)
      File "C:\Users\xxxxx\Documents\WebUI-Stable-Diffusion\stable-diffusion-webui\venv\lib\site-packages\xformers\ops\fmha\flash.py", line 177, in _convert_input_format
        key=key.reshape([batch * seqlen_kv, num_heads, head_dim_q]),
    RuntimeError: shape '[81920, 8, 40]' is invalid for input of size 3276800

Additional information

No response

[huchenlei]

Can you provide more information on how to reproduce the issue? Running reference_only seems fine in my local environment.

[garugann]

I also encountered a similar error. It seems to occur when using --xformers in version 1.7.
It seems that the error does not occur if vemv is deleted and --xformers is not used.
I have not thoroughly verified it, and it is not exactly the same error, so this may not be the cause.
I would be happy if it is helpful.

[huchenlei]

Which xformers version do you use @garugann. With --xformers flag in 1.7.0 A1111, it seems to work fine for me.

[garugann]

version: v1.7.0  •  python: 3.10.11  •  torch: 2.0.1+cu118  •  xformers: 0.0.20  •  gradio: 3.41.2  •  checkpoint: 735df1f05d

It seems that an error occurs in this environment. To be honest, I don't know if this is the correct cause. In the meantime, I can generate Reference successfully when --xformers is n/a.

[huchenlei]

I have following env and reference is worknig fine:
version: v1.7.0-RC-5-gf92d6149  •  python: 3.10.6  •  torch: 2.0.1+cu118  •  xformers: 0.0.20  •  gradio: 3.41.2  •  checkpoint: 79e42fb744

[garugann]

While I was comparing it to a completely new environment, I realized that the config.json file might be outdated. After deleting it and resetting the config, it seems to be operating without any problems even in the same environment.
version: v1.7.0  •  python: 3.10.11  •  torch: 2.0.1+cu118  •  xformers: 0.0.20  •  gradio: 3.41.2  •

[garugann]

I think it might be Hypertile. If I turn it on or off in the settings, the error appears or disappears.

[zongmi]

Traceback (most recent call last):
File "D:\gongxiang\stable-diffusion-webui\modules\call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\call_queue.py", line 36, in f
res = func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\txt2img.py", line 55, in txt2img
processed = processing.process_images(p)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\processing.py", line 734, in process_images
res = process_images_inner(p)
^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 41, in processing_process_images_hijack
return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\processing.py", line 868, in process_images_inner
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 435, in process_sample
return process.sample_before_CN_hack(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\processing.py", line 1142, in sample
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 235, in sample
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\sd_samplers_common.py", line 261, in launch_sampling
return func()
^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 235, in
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\sampling.py", line 594, in sample_dpmpp_2m
denoised = model(x, sigmas[i] * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\sd_samplers_cfg_denoiser.py", line 169, in forward
x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict(cond_in, image_cond_in))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\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 "D:\gongxiang\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 138, in get_eps
return self.inner_model.apply_model(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\sd_models_xl.py", line 37, in apply_model
return self.model(x, t, cond)
^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1568, in _call_impl
result = forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\sd_hijack_utils.py", line 17, in
setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\sd_hijack_utils.py", line 28, in call
return self.__orig_func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\repositories\generative-models\sgm\modules\diffusionmodules\wrappers.py", line 28, in forward
return self.diffusion_model(
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 845, in forward_webui
raise e
File "D:\gongxiang\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 842, in forward_webui
return forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 720, in forward
outer.original_forward(
File "D:\gongxiang\stable-diffusion-webui\modules\sd_unet.py", line 91, in UNetModel_forward
return original_forward(self, x, timesteps, context, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\repositories\generative-models\sgm\modules\diffusionmodules\openaimodel.py", line 993, in forward
h = module(h, emb, context)
^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 898, in hacked_group_norm_forward
x = self.original_forward_cn_hijack(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\repositories\generative-models\sgm\modules\diffusionmodules\openaimodel.py", line 100, in forward
x = layer(x, context)
^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\repositories\generative-models\sgm\modules\attention.py", line 627, in forward
x = block(x, context=context[i])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\repositories\generative-models\sgm\modules\attention.py", line 459, in forward
return checkpoint(
^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\repositories\generative-models\sgm\modules\diffusionmodules\util.py", line 165, in checkpoint
return CheckpointFunction.apply(func, len(inputs), *args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\autograd\function.py", line 539, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\repositories\generative-models\sgm\modules\diffusionmodules\util.py", line 182, in forward
output_tensors = ctx.run_function(*ctx.input_tensors)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 889, in hacked_basic_transformer_inner_forward
self_attn1 = self.attn1(x_norm1, context=self_attention_context)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1527, in call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\extensions-builtin\hypertile\hypertile.py", line 307, in wrapper
out = params.forward(x, *args[1:], **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\gongxiang\stable-diffusion-webui\modules\sd_hijack_optimizations.py", line 496, in xformers_attention_forward
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=get_xformers_flash_attention_op(q, k, v))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\xformers\ops\fmha_init.py", line 223, in memory_efficient_attention
return memory_efficient_attention(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\xformers\ops\fmha_init.py", line 321, in _memory_efficient_attention
return memory_efficient_attention_forward(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\xformers\ops\fmha_init.py", line 334, in _memory_efficient_attention_forward
inp.validate_inputs()
File "C:\Users\Owner\AppData\Local\Programs\Python\Python311\Lib\site-packages\xformers\ops\fmha\common.py", line 197, in validate_inputs
raise ValueError(
ValueError: Incompatible shapes for attention inputs:
query.shape: torch.Size([4, 512, 10, 64])
key.shape : torch.Size([2, 1024, 10, 64])
value.shape: torch.Size([2, 1024, 10, 64])
HINT: We don't support broadcasting, please use expand yourself before calling memory_efficient_attention if you need to

[zongmi]

The same error comes from the hypertile call. At the moment I have no intention of tracking down whether it is a problem with hypertile or python 3.11. Either I roll back the environment to xformers-17, which I don't want to do. I currently choose to turn off hypertile to avoid this error. Maybe I should file a bug with webui?

[negu63]

Environment
os: window10
browser: firefox
gpu: nvidia rtx 4070 ti
cpu: intel
cuda: 11.8
cudnn: 8.9.7

Webui
version: v1.7.0
python: 3.10.13
torch: 2.0.1+cu118
xformers: 0.0.20
gradio: 3.41.2
checkpoint: 1449e5b0b9
arguments: --xformers --xformers-flash-attention --no-half-vae

Controlnet
version: v1.1.440
checkpoint: 9a5f288
preprocessor: canny
model: controlnetxlCNXL_bdsqlszCanny [a74daa41]

In addition to canny, I get an error

Model
AnimagineXL_V3 (base on SDXL 1.0)

Vae
sdxl-vae

---

I'm experiencing something similar, albeit a different error.

I'm using Tiled VAE with Hypertile and DeepCache.

I don't use Lora or Embedding.

In my case, turning off xformers was the same.

When using the SDXL model, if I enable Hypertile or DeepCache and use ControlNet, I get an error.

The error is as follows

RuntimeError: Sizes of tensors must match except in dimension 2. Expected size 4096 but got size 2048 for tensor number 1 in the list.

📃Error Message (full)

---

2024-02-13 19:38:22,188 - ControlNet - INFO - unit_separate = False, style_align = False
2024-02-13 19:38:22,196 - ControlNet - INFO - Loading model from cache: controlnetxlCNXL_bdsqlszOpenpose [23893c0e]
2024-02-13 19:38:22,196 - ControlNet - INFO - Loading model: controlnetxlCNXL_bdsqlszOpenpose [23893c0e]
2024-02-13 19:38:22,393 - ControlNet - INFO - Loaded state_dict from [C:\stable-diffusion-webui\models\ControlNet\controlnetxlCNXL_bdsqlszOpenpose.safetensors]
2024-02-13 19:38:23,032 - ControlNet - INFO - ControlNet model controlnetxlCNXL_bdsqlszOpenpose 23893c0e loaded.
2024-02-13 19:38:23,053 - ControlNet - INFO - Using preprocessor: dw_openpose_full
2024-02-13 19:38:23,053 - ControlNet - INFO - preprocessor resolution = 512
2024-02-13 19:38:23,092 - ControlNet - INFO - ControlNet Hooked - Time = 0.9101603031158447
0%| | 0/20 [00:00<?, ?it/s]
*** Error completing request
*** Arguments: ('task(notaecqyquncb48)', 'sdxl-ktgw-marin, medium breasts, pinkred eyes, long eyelashes, pink eyeliner, (lower eyelashes), black eyelashes, nails, shiny hair, straight hair, (gradient hair (blond:lightpink:0.8) hair), long hair sleeves rolled up, coin_choker, pierce, slender, skindantation, :>, choke blush +++ (white collared_shirt) (saxe_blue loose_necktie) (plaid_pleated_mini_skirt skyblue skirt), extremely quality extremely detailed, illustration, contrapposto, cute anime face cinematic lighting cinematic angle', 'lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name worst quality, low quality', [], 20, 'DPM++ 2M Karras', 1, 1, 7, 1024, 1024, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], <gradio.routes.Request object at 0x000002162AB58AC0>, 0, False, '', 0.8, 442993243, False, -1, 0, 0, 0, False, False, {'ad_model': 'face_yolov8n.pt', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'DPM++ 2M Karras', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, {'ad_model': 'None', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'DPM++ 2M Karras', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, False, 'MultiDiffusion', False, True, 1024, 1024, 96, 96, 48, 4, 'None', 2, False, 10, 1, 1, 64, False, False, False, False, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, True, 1536, 96, True, True, True, True, True, False, 1, False, False, False, 1.1, 1.5, 100, 0.7, False, False, True, False, False, 0, 'Gustavosta/MagicPrompt-Stable-Diffusion', '', UiControlNetUnit(enabled=True, module='dw_openpose_full', model='controlnetxlCNXL_bdsqlszOpenpose [23893c0e]', weight=1, image={'image': array([[[ 88, 91, 125],
*** [ 88, 92, 127],
*** [ 89, 91, 125],
*** ...,
*** [131, 129, 158],
*** [131, 131, 158],
*** [131, 130, 159]],

---

*** [[ 88, 91, 125],
*** [ 89, 91, 127],
*** [ 89, 90, 125],
*** ...,
*** [130, 129, 158],
*** [131, 129, 158],
*** [131, 129, 159]],

---

*** [[ 88, 90, 124],
*** [ 88, 90, 124],
*** [ 89, 90, 124],
*** ...,
*** [130, 128, 157],
*** [130, 129, 157],
*** [130, 128, 158]],

---

*** ...,

---

*** [[150, 128, 146],
*** [168, 145, 167],
*** [185, 158, 181],
*** ...,
*** [ 62, 54, 65],
*** [ 62, 54, 65],
*** [ 62, 54, 65]],

---

*** [[139, 116, 132],
*** [155, 132, 154],
*** [183, 161, 182],
*** ...,
*** [ 62, 54, 65],
*** [ 62, 54, 67],
*** [ 62, 54, 66]],

---

*** [[145, 126, 134],
*** [145, 124, 141],
*** [170, 147, 166],
*** ...,
*** [ 63, 53, 64],
*** [ 63, 54, 66],
*** [ 63, 55, 65]]], dtype=uint8), 'mask': array([[[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],

---

*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],

---

*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],

---

*** ...,

---

*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],

---

*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]],

---

*** [[0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0],
*** ...,
*** [0, 0, 0],
*** [0, 0, 0],
*** [0, 0, 0]]], dtype=uint8)}, resize_mode='Crop and Resize', low_vram=False, processor_res=512, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', inpaint_crop_input_image=True, hr_option='Both', save_detected_map=True, advanced_weighting=None), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', inpaint_crop_input_image=False, hr_option='Both', save_detected_map=True, advanced_weighting=None), UiControlNetUnit(enabled=False, module='none', model='None', weight=1, image=None, resize_mode='Crop and Resize', low_vram=False, processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', inpaint_crop_input_image=False, hr_option='Both', save_detected_map=True, advanced_weighting=None), False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, False, False, False, False, '#000000', False, None, None, False, None, None, False, None, None, False, 50) {}
Traceback (most recent call last):
File "C:\stable-diffusion-webui\modules\call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
File "C:\stable-diffusion-webui\modules\call_queue.py", line 36, in f
res = func(*args, **kwargs)
File "C:\stable-diffusion-webui\modules\txt2img.py", line 55, in txt2img
processed = processing.process_images(p)
File "C:\stable-diffusion-webui\modules\processing.py", line 734, in process_images
res = process_images_inner(p)
File "C:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 41, in processing_process_images_hijack
return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
File "C:\stable-diffusion-webui\modules\processing.py", line 868, in process_images_inner
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
File "C:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\hook.py", line 438, in process_sample
return process.sample_before_CN_hack(*args, **kwargs)
File "C:\stable-diffusion-webui\modules\processing.py", line 1142, in sample
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
File "C:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 235, in sample
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "C:\stable-diffusion-webui\modules\sd_samplers_common.py", line 261, in launch_sampling
return func()
File "C:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 235, in
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "C:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\sampling.py", line 594, in sample_dpmpp_2m
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\stable-diffusion-webui\modules\sd_samplers_cfg_denoiser.py", line 188, in forward
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict(c_crossattn, image_cond_in[a:b]))
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\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:\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:\stable-diffusion-webui\modules\sd_models_xl.py", line 37, in apply_model
return self.model(x, t, cond)
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\stable-diffusion-webui\modules\sd_hijack_utils.py", line 17, in
setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
File "C:\stable-diffusion-webui\modules\sd_hijack_utils.py", line 28, in call
return self.__orig_func(*args, **kwargs)
File "C:\stable-diffusion-webui\repositories\generative-models\sgm\modules\diffusionmodules\wrappers.py", line 28, in forward
return self.diffusion_model(
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\stable-diffusion-webui\extensions\sd-webui-deepcache-standalone\deepcache.py", line 133, in hijacked_unet_forward
h = forward_timestep_embed(module, h, emb, context)
File "C:\stable-diffusion-webui\extensions\sd-webui-deepcache-standalone\scripts\forward_timestep_embed_patch.py", line 39, in forward_timestep_embed
x = layer(x, context)
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\stable-diffusion-webui\repositories\generative-models\sgm\modules\attention.py", line 627, in forward
x = block(x, context=context[i])
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\stable-diffusion-webui\repositories\generative-models\sgm\modules\attention.py", line 459, in forward
return checkpoint(
File "C:\stable-diffusion-webui\repositories\generative-models\sgm\modules\diffusionmodules\util.py", line 165, in checkpoint
return CheckpointFunction.apply(func, len(inputs), *args)
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\autograd\function.py", line 506, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
File "C:\stable-diffusion-webui\repositories\generative-models\sgm\modules\diffusionmodules\util.py", line 182, in forward
output_tensors = ctx.run_function(*ctx.input_tensors)
File "C:\stable-diffusion-webui\repositories\generative-models\sgm\modules\attention.py", line 467, in _forward
self.attn1(
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\stable-diffusion-webui\extensions-builtin\hypertile\hypertile.py", line 307, in wrapper
out = params.forward(x, *args[1:], **kwargs)
File "C:\stable-diffusion-webui\modules\sd_hijack_optimizations.py", line 482, in xformers_attention_forward
q_in = self.to_q(x)
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "C:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\controlnet_lllite.py", line 215, in forward
hack = hack + module(x, current_h_shape) * weight
File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\controlnet_lllite.py", line 99, in forward
cx = torch.cat([cx, self.down(x)], dim=1 if self.is_conv2d else 2)
RuntimeError: Sizes of tensors must match except in dimension 2. Expected size 4096 but got size 2048 for tensor number 1 in the list.

---