Bug: The size of tensor a (640) must match the size of tensor b (320)

[bluadept]

PLEASE READ BEFORE SUBMITTING AN ISSUE

MagicQuill is not a commercial software but a research project. While we strive to improve and maintain it, support is provided on a best-effort basis. Please be patient and respectful in your communications.
To help us respond faster and better, please ensure the following:

1. Search Existing Resources: Have you looked through the documentation (e.g., hardware requirement and setup steps), and searched online for potential solutions?
2. Avoid Duplication: Check if a similar issue already exists.

If the issue persists, fill out the details below.

---

Checklist

• I have searched the documentation and FAQs.
• I have searched for similar issues but couldn’t find a solution.
• I have provided clear and detailed information about the issue.

---

Issue/Feature Request Description

Type of Issue:

• Bug

Summary:
Installed MagicQuill on my Windows Server.
Windows Server 2022
Intel Core I9 13900
16 GB of memory
NVIDIA T1000 8G GPU

---

Steps to Reproduce (For Bugs Only)

1. Pull the image Girl_at_Beach.jpg into the copy image section of the webpage (this operates normally)
2. using the + quill place a small area where the image will be placed.
3. Click the run button which runs for a while then gives the error.

Expected Behavior:
Add an item to the picture

Actual Behavior:
Starts to process then give error message
The size of tensor a (640) must match the size of tensor b (320)
Does not matter what the size of the edit is

---

Additional Context/Details

This is the log running for the instance of MagicQuill
Requested to load SD1ClipModel
Loading 1 new model
Apply edge controlnet
C:\Windows\System32\MagicQuill\MagicQuill\pidi.py:334: UserWarning: The torch.cuda.DtypeTensor constructors are no longer recommended. It's best to use methods such as torch.tensor(data, dtype=, device='cuda') to create tensors. (Triggered internally at ..\torch\csrc\tensor\python_tensor.cpp:85.)
buffer = torch.cuda.FloatTensor(shape[0], shape[1], 5 * 5).fill_(0)
Base model type: SD1.5
BrushNet image.shape = torch.Size([1, 512, 512, 3]) mask.shape = torch.Size([1, 512, 512])
Requested to load AutoencoderKL
Loading 1 new model
loading in lowvram mode 64.0
BrushNet CL: image_latents shape = torch.Size([1, 4, 64, 64]) interpolated_mask shape = torch.Size([1, 1, 64, 64])
Requested to load BaseModel
Requested to load ControlNet
Loading 2 new models
loading in lowvram mode 64.0
loading in lowvram mode 64.0
0%| | 0/20 [00:00<?, ?it/s]BrushNet inference: do_classifier_free_guidance is True
BrushNet inference, step = 0: image batch = 1, got 2 latents, starting from 0
BrushNet inference: sample torch.Size([2, 4, 64, 64]) , CL torch.Size([2, 5, 64, 64]) dtype torch.float16
C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\diffusers\models\resnet.py:323: FutureWarning: scale is deprecated and will be removed in version 1.0.0. The scale argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. scale should directly be passed while calling the underlying pipeline component i.e., via cross_attention_kwargs.
deprecate("scale", "1.0.0", deprecation_message)
BrushNet can't find <class 'comfy.ops.disable_weight_init.Conv2d'> layer in 0 input block: None
0%| | 0/20 [00:03<?, ?it/s]
Traceback (most recent call last):
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\gradio\queueing.py", line 624, in process_events
response = await route_utils.call_process_api(
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\gradio\route_utils.py", line 323, in call_process_api
output = await app.get_blocks().process_api(
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\gradio\blocks.py", line 2018, in process_api
result = await self.call_function(
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\gradio\blocks.py", line 1567, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\anyio_backends_asyncio.py", line 2505, in run_sync_in_worker_thread
return await future
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\anyio_backends_asyncio.py", line 1005, in run
result = context.run(func, *args)
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\gradio\utils.py", line 846, in wrapper
response = f(*args, **kwargs)
File "C:\Windows\System32\MagicQuill\gradio_run.py", line 155, in generate_image_handler
res = generate(
File "C:\Windows\System32\MagicQuill\gradio_run.py", line 123, in generate
latent_samples, final_image, lineart_output, color_output = scribbleColorEditModel.process(
File "C:\Windows\System32\MagicQuill\MagicQuill\scribble_color_edit.py", line 110, in process
latent_samples = self.ksampler.sample(
File "C:\Windows\System32\MagicQuill\MagicQuill\comfyui_utils.py", line 154, in sample
return self.common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfyui_utils.py", line 146, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\sample.py", line 43, in sample
samples = sampler.sample(noise, positive, negative, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\samplers.py", line 794, in sample
return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
File "C:\Windows\System32\MagicQuill\MagicQuill\model_patch.py", line 120, in modified_sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\samplers.py", line 683, in sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\samplers.py", line 662, in inner_sample
samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\samplers.py", line 567, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\k_diffusion\sampling.py", line 159, in sample_euler_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\samplers.py", line 291, in call
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\samplers.py", line 649, in call
return self.predict_noise(*args, **kwargs)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\samplers.py", line 652, in predict_noise
return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\samplers.py", line 277, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\samplers.py", line 224, in calc_cond_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 "C:\Windows\System32\MagicQuill\MagicQuill\model_patch.py", line 52, in brushnet_model_function_wrapper
return apply_model_method(x, timestep, **options_dict['c'])
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\model_base.py", line 113, in apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Windows\System32\MagicQuill\MagicQuill\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 852, 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 "C:\Windows\System32\MagicQuill\MagicQuill\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 44, in forward_timestep_embed
x = layer(x, context, transformer_options)
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\ProgramData\anaconda3\envs\MagicQuill\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Windows\System32\MagicQuill\MagicQuill\brushnet_nodes.py", line 1070, in forward_patched_by_brushnet
h += to_add.to(h.dtype).to(h.device)
RuntimeError: The size of tensor a (640) must match the size of tensor b (320) at non-singleton dimension 1

---

Environment

• OS:
• Windows Server 2022
• Version:
• Any Relevant Dependencies:
  

---

[zliucz]

Hi, check this issues#43.