[Bug]: controlnet

### Checklist

- [ ] The issue exists after disabling all extensions
- [X] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
- [x] The issue exists in the current version of the webui
- [x] The issue has not been reported before recently
- [ ] The issue has been reported before but has not been fixed yet

### What happened?

openpose works
photoID works
reference dont work (console below)
depth dont work (similar error: TypeError: 'NoneType' object is not iterable)

### Steps to reproduce the problem

**all errors in tab "img2img"**

most works in txt2img

### What should have happened?

-

### What browsers do you use to access the UI ?

_No response_

### Sysinfo

win10
rtx4060
forge version: f0.0.17v1.8.0rc

### Console logs

```Shell
---
2024-05-31 15:17:13,385 - ControlNet - INFO - ControlNet Input Mode: InputMode.SIMPLE
2024-05-31 15:17:13,385 - ControlNet - INFO - Using preprocessor: reference_only
2024-05-31 15:17:13,385 - ControlNet - INFO - preprocessor resolution = 0.5
2024-05-31 15:17:13,445 - ControlNet - INFO - Current ControlNet ControlModelPatcher: Not Needed
2024-05-31 15:17:14,020 - ControlNet - INFO - ControlNet Method reference_only patched.
To load target model SDXL
Begin to load 1 model
Reuse 1 loaded models
[Memory Management] Current Free GPU Memory (MB) = 4634.16552734375
[Memory Management] Model Memory (MB) = 0.0
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 3610.16552734375
Moving model(s) has taken 0.05 seconds
0%| | 0/16 [00:00
samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "e:\WebUI_Forge\system\python\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "E:\WebUI_Forge\webui\repositories\k-diffusion\k_diffusion\sampling.py", line 594, in sample_dpmpp_2m
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "e:\WebUI_Forge\system\python\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "e:\WebUI_Forge\system\python\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "E:\WebUI_Forge\webui\modules\sd_samplers_cfg_denoiser.py", line 182, in forward
denoised = forge_sampler.forge_sample(self, denoiser_params=denoiser_params,
File "E:\WebUI_Forge\webui\modules_forge\forge_sampler.py", line 88, in forge_sample
denoised = sampling_function(model, x, timestep, uncond, cond, cond_scale, model_options, seed)
File "E:\WebUI_Forge\webui\ldm_patched\modules\samplers.py", line 289, in sampling_function
cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond_, x, timestep, model_options)
File "E:\WebUI_Forge\webui\ldm_patched\modules\samplers.py", line 256, in calc_cond_uncond_batch
output = model_options['model_function_wrapper'](model.apply_model, {"input": input_x, "timestep": timestep_, "c": c, "cond_or_uncond": cond_or_uncond}).chunk(batch_chunks)
File "e:\WebUI_Forge\system\python\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "E:\WebUI_Forge\webui\extensions-builtin\sd_forge_multidiffusion\lib_multidiffusion\tiled_diffusion.py", line 428, in __call__
x_tile_out = model_function(x_tile, ts_tile, **c_tile)
File "E:\WebUI_Forge\webui\ldm_patched\modules\model_base.py", line 90, in apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
File "e:\WebUI_Forge\system\python\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "e:\WebUI_Forge\system\python\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "E:\WebUI_Forge\webui\ldm_patched\ldm\modules\diffusionmodules\openaimodel.py", line 867, in forward
h = forward_timestep_embed(module, h, emb, context, transformer_options, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator)
File "E:\WebUI_Forge\webui\ldm_patched\ldm\modules\diffusionmodules\openaimodel.py", line 55, in forward_timestep_embed
x = layer(x, context, transformer_options)
File "e:\WebUI_Forge\system\python\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "e:\WebUI_Forge\system\python\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "E:\WebUI_Forge\webui\ldm_patched\ldm\modules\attention.py", line 620, in forward
x = block(x, context=context[i], transformer_options=transformer_options)
File "e:\WebUI_Forge\system\python\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "e:\WebUI_Forge\system\python\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "E:\WebUI_Forge\webui\ldm_patched\ldm\modules\attention.py", line 447, in forward
return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint)
File "E:\WebUI_Forge\webui\ldm_patched\ldm\modules\diffusionmodules\util.py", line 194, in checkpoint
return func(*inputs)
File "E:\WebUI_Forge\webui\ldm_patched\ldm\modules\attention.py", line 504, in _forward
n = attn1_replace_patch[block_attn1](n, context_attn1, value_attn1, extra_options)
File "E:\WebUI_Forge\webui\extensions-builtin\forge_preprocessor_reference\scripts\forge_reference.py", line 172, in attn1_proc
o_c = sdp(q_c, zero_cat(k_c, k_r, dim=1), zero_cat(v_c, v_r, dim=1), transformer_options)
File "E:\WebUI_Forge\webui\extensions-builtin\forge_preprocessor_reference\scripts\forge_reference.py", line 29, in zero_cat
return torch.cat([a, b], dim=dim)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 1 but got size 2 for tensor number 1 in the list.
Sizes of tensors must match except in dimension 1. Expected size 1 but got size 2 for tensor number 1 in the list.
*** Error completing request
*** Arguments: ('task(mfhbttqrzlyemjk)', 0, 'boy sitting in the room', '', [], , None, None, None, None, None, None, 20, 'DPM++ 2M Karras', 4, 0, 1, 1, 1, 3, 1.5, 0.78, 0.0, 640, 1024, 1, 0, 0, 32, 0, '', '', '', [], False, [], '', , 0, False, 1, 0.5, 4, 0, 0.5, 2, False, '', 0.8, -1, False, -1, 0, 0, 0, False, False, {'ad_model': 'face_yolov8n.pt', 'ad_model_classes': '', 'ad_tap_enable': True, '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_scheduler': 'Use same scheduler', '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_model_classes': '', 'ad_tap_enable': True, '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_scheduler': 'Use same scheduler', '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_model_classes': '', 'ad_tap_enable': True, '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_scheduler': 'Use same scheduler', '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_model_classes': '', 'ad_tap_enable': True, '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_scheduler': 'Use same scheduler', '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': ()}, 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, 0.5, 0, ControlNetUnit(input_mode=, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=array([[[191, 173, 159],
*** [191, 173, 159],
*** [191, 173, 159],
*** ...,
*** [216, 214, 202],
*** [214, 210, 199],
*** [211, 207, 196]],
***
*** [[191, 173, 159],
*** [191, 173, 159],
*** [191, 173, 159],
*** ...,
*** [219, 217, 205],
*** [217, 213, 202],
*** [214, 210, 199]],
***
*** [[191, 173, 159],
*** [191, 173, 159],
*** [191, 173, 159],
*** ...,
*** [223, 221, 209],
*** [221, 217, 206],
*** [218, 214, 203]],
***
*** ...,
***
*** [[221, 204, 196],
*** [218, 201, 193],
*** [212, 195, 187],
*** ...,
*** [202, 179, 161],
*** [218, 192, 177],
*** [224, 196, 182]],
***
*** [[217, 197, 190],
*** [206, 186, 179],
*** [188, 169, 162],
*** ...,
*** [224, 201, 183],
*** [226, 200, 185],
*** [205, 179, 164]],
***
*** [[213, 190, 184],
*** [197, 174, 168],
*** [172, 152, 145],
*** ...,
*** [193, 170, 152],
*** [173, 147, 132],
*** [154, 128, 113]]], dtype=uint8), mask_image=None, hr_option='Both', enabled=True, module='reference_only', model='None', weight=1, image={'image': array([[[191, 173, 159],
*** [191, 173, 159],
*** [191, 173, 159],
*** ...,
*** [216, 214, 202],
*** [214, 210, 199],
*** [211, 207, 196]],
***
*** [[191, 173, 159],
*** [191, 173, 159],
*** [191, 173, 159],
*** ...,
*** [219, 217, 205],
*** [217, 213, 202],
*** [214, 210, 199]],
***
*** [[191, 173, 159],
*** [191, 173, 159],
*** [191, 173, 159],
*** ...,
*** [223, 221, 209],
*** [221, 217, 206],
*** [218, 214, 203]],
***
*** ...,
***
*** [[221, 204, 196],
*** [218, 201, 193],
*** [212, 195, 187],
*** ...,
*** [202, 179, 161],
*** [218, 192, 177],
*** [224, 196, 182]],
***
*** [[217, 197, 190],
*** [206, 186, 179],
*** [188, 169, 162],
*** ...,
*** [224, 201, 183],
*** [226, 200, 185],
*** [205, 179, 164]],
***
*** [[213, 190, 184],
*** [197, 174, 168],
*** [172, 152, 145],
*** ...,
*** [193, 170, 152],
*** [173, 147, 132],
*** [154, 128, 113]]], 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', processor_res=0.5, threshold_a=0.5, threshold_b=0.5, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='ControlNet is more important', save_detected_map=True), ControlNetUnit(input_mode=, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=array([[[ 9, 9, 9],
*** [ 9, 9, 9],
*** [ 9, 9, 9],
*** ...,
*** [ 34, 34, 34],
*** [ 33, 33, 33],
*** [ 32, 32, 32]],
***
*** [[ 9, 9, 9],
*** [ 9, 9, 9],
*** [ 10, 10, 10],
*** ...,
*** [ 34, 34, 34],
*** [ 33, 33, 33],
*** [ 32, 32, 32]],
***
*** [[ 10, 10, 10],
*** [ 10, 10, 10],
*** [ 10, 10, 10],
*** ...,
*** [ 35, 35, 35],
*** [ 34, 34, 34],
*** [ 33, 33, 33]],
***
*** ...,
***
*** [[248, 248, 248],
*** [249, 249, 249],
*** [249, 249, 249],
*** ...,
*** [195, 195, 195],
*** [195, 195, 195],
*** [195, 195, 195]],
***
*** [[250, 250, 250],
*** [250, 250, 250],
*** [251, 251, 251],
*** ...,
*** [196, 196, 196],
*** [196, 196, 196],
*** [196, 196, 196]],
***
*** [[250, 250, 250],
*** [251, 251, 251],
*** [251, 251, 251],
*** ...,
*** [197, 197, 197],
*** [197, 197, 197],
*** [197, 197, 197]]], dtype=uint8), mask_image=None, hr_option='Both', enabled=False, module='depth_midas', model='t2i-adapter_diffusers_xl_depth_midas [9c183166]', weight=1, image={'image': array([[[191, 173, 159],
*** [191, 173, 159],
*** [191, 173, 159],
*** ...,
*** [216, 214, 202],
*** [214, 210, 199],
*** [211, 207, 196]],
***
*** [[191, 173, 159],
*** [191, 173, 159],
*** [191, 173, 159],
*** ...,
*** [219, 217, 205],
*** [217, 213, 202],
*** [214, 210, 199]],
***
*** [[191, 173, 159],
*** [191, 173, 159],
*** [191, 173, 159],
*** ...,
*** [223, 221, 209],
*** [221, 217, 206],
*** [218, 214, 203]],
***
*** ...,
***
*** [[221, 204, 196],
*** [218, 201, 193],
*** [212, 195, 187],
*** ...,
*** [202, 179, 161],
*** [218, 192, 177],
*** [224, 196, 182]],
***
*** [[217, 197, 190],
*** [206, 186, 179],
*** [188, 169, 162],
*** ...,
*** [224, 201, 183],
*** [226, 200, 185],
*** [205, 179, 164]],
***
*** [[213, 190, 184],
*** [197, 174, 168],
*** [172, 152, 145],
*** ...,
*** [193, 170, 152],
*** [173, 147, 132],
*** [154, 128, 113]]], 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', processor_res=512, threshold_a=0.5, threshold_b=0.5, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), ControlNetUnit(input_mode=, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], generated_image=None, mask_image=None, hr_option='Both', enabled=False, module='None', model='None', weight=1, image=None, resize_mode='Crop and Resize', processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode='Balanced', save_detected_map=True), False, 7, 1, 'Constant', 0, 'Constant', 0, 1, 'enable', 'MEAN', 'AD', 1, False, 1.01, 1.02, 0.99, 0.95, False, 0.5, 2, False, 256, 2, 0, False, False, 3, 2, 0, 0.35, True, 'bicubic', 'bicubic', False, 0, 'anisotropic', 0, 'reinhard', 100, 0, 'subtract', 0, 0, 'gaussian', 'add', 0, 100, 127, 0, 'hard_clamp', 5, 0, 'None', 'None', True, 'MultiDiffusion', 768, 768, 64, 4, False, False, False, '* `CFG Scale` should be 2 or lower.', True, True, '', '', True, 50, True, 1, 0, False, 4, 0.5, 'Linear', 'None', '

Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8

', 128, 8, ['left', 'right', 'up', 'down'], 1, 0.05, 128, 4, 0, ['left', 'right', 'up', 'down'], False, False, 'positive', 'comma', 0, False, False, 'start', '', '

Will upscale the image by the selected scale factor; use width and height sliders to set tile size

', 64, 0, 2, 1, '', [], 0, '', [], 0, '', [], True, False, False, False, False, False, False, 0, False) {}
Traceback (most recent call last):
File "E:\WebUI_Forge\webui\modules\call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
TypeError: 'NoneType' object is not iterable

---
```

### Additional information

_No response_

Start with extensions-builtin/forge_preprocessor_reference/scripts/forge_reference.py, especially zero_cat and attn1_proc, then trace the img2img path through modules/img2img.py and modules/processing.py. Reproduce the reported ControlNet reference_only and depth cases in img2img and verify that tensor dimensions no longer trigger the reported RuntimeError.

Written by the indexing model from the issue text.