shiimizu / comfyui-tileddiffusion Goto Github PK

View Code? Open in Web Editor NEW

177.0 6.0 9.0 169 KB

Tiled Diffusion, MultiDiffusion, Mixture of Diffusers, and optimized VAE

Python 100.00%

comfyui image-generation large-image multidiffusion stable-diffusion vramsaving

comfyui-tileddiffusion's Introduction

Tiled Diffusion & VAE for ComfyUI

Check out the SD-WebUI extension for more information.

This extension enables large image drawing & upscaling with limited VRAM via the following techniques:

Two SOTA diffusion tiling algorithms: Mixture of Diffusers and MultiDiffusion
pkuliyi2015 & Kahsolt's Tiled VAE algorithm.
~~pkuliyi2015 & Kahsolt's TIled Noise Inversion for better upscaling.~~

Note

Sizes/dimensions are in pixels and then converted to latent-space sizes.

Features

Tiled Diffusion

Tip

Set tile_overlap to 0 and denoise to 1 to see the tile seams and then adjust the options to your needs. Also, increase tile_batch_size to increase speed (if your machine can handle it).

Name	Description
`method`	Tiling strategy. `MultiDiffusion` or `Mixture of Diffusers`.
`tile_width`	Tile's width
`tile_height`	Tile's height
`tile_overlap`	Tile's overlap
`tile_batch_size`	The number of tiles to process in a batch

How can I specify the tiles' arrangement?

If you have the Math Expression node (or something similar), you can use that to pass in the latent that's passed in your KSampler and divide the tile_height/tile_width by the number of rows/columns you want.

C = number of columns you want
R = number of rows you want

pixel width of input image or latent // C = tile_width
pixel height of input image or latent // R = tile_height

Tiled VAE

The recommended tile sizes are given upon the creation of the node based on the available VRAM.

Note

Enabling fast for the decoder may produce images with slightly higher contrast and brightness.

Name Description

Name	Description
`tile_size`	The image is split into tiles, which are then padded with 11/32 pixels' in the decoder/encoder.
`fast`	When Fast Mode is disabled: The original VAE forward is decomposed into a task queue and a task worker, which starts to process each tile. When GroupNorm is needed, it suspends, stores current GroupNorm mean and var, send everything to RAM, and turns to the next tile. After all GroupNorm means and vars are summarized, it applies group norm to tiles and continues. A zigzag execution order is used to reduce unnecessary data transfer. When Fast Mode is enabled: The original input is downsampled and passed to a separate task queue. Its group norm parameters are recorded and used by all tiles' task queues. Each tile is separately processed without any RAM-VRAM data transfer. After all tiles are processed, tiles are written to a result buffer and returned.
`color_fix`	Only estimate GroupNorm before downsampling, i.e., run in a semi-fast mode. Only for the encoder. Can restore colors if tiles are too small.

tile_size

The image is split into tiles, which are then padded with 11/32 pixels' in the decoder/encoder.

fast

When Fast Mode is disabled:

The original VAE forward is decomposed into a task queue and a task worker, which starts to process each tile.

When GroupNorm is needed, it suspends, stores current GroupNorm mean and var, send everything to RAM, and turns to the next tile.

After all GroupNorm means and vars are summarized, it applies group norm to tiles and continues.

A zigzag execution order is used to reduce unnecessary data transfer.

When Fast Mode is enabled:

The original input is downsampled and passed to a separate task queue.

Its group norm parameters are recorded and used by all tiles' task queues.

Each tile is separately processed without any RAM-VRAM data transfer.

After all tiles are processed, tiles are written to a result buffer and returned.

color_fix

Only estimate GroupNorm before downsampling, i.e., run in a semi-fast mode.

Only for the encoder. Can restore colors if tiles are too small.

Workflows

The following images can be loaded in ComfyUI.

Simple upscale.

4x upscale. 3 passes.

Citation

@article{jimenez2023mixtureofdiffusers,
  title={Mixture of Diffusers for scene composition and high resolution image generation},
  author={Álvaro Barbero Jiménez},
  journal={arXiv preprint arXiv:2302.02412},
  year={2023}
}

@article{bar2023multidiffusion,
  title={MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation},
  author={Bar-Tal, Omer and Yariv, Lior and Lipman, Yaron and Dekel, Tali},
  journal={arXiv preprint arXiv:2302.08113},
  year={2023}
}

comfyui-tileddiffusion's People

Contributors

Stargazers

Watchers

Forkers

assassindesign soliver84 johndpope brgrp flowtyone promeg aravindhv10 marcojoao

comfyui-tileddiffusion's Issues

Controlnet image applies to each tile insted of the hole image.

After ca0ed33 Apply ControlNet (Advanced) applies to each tile individually creating a grid of cloned images.
example

Tile controlnet uses the conditioning from the previous generation with TiledDiffusion

Have a workflow where the first generation works great, but then subsequent generations use the tile controlnet from the previous generation instead of the current one. This effect is not seen if I bypass the Tiled Diffusion node. Seems there's something strange in the caching/application of the conditioning. Using Advanced Controlnet nodes.

Awesome node, small feature request!

this is such an awesome node... thank you for bringing this into ComfyUI!
got a feature request. if possible, is there a way to get the tiles out to be shown separately? ideally i'd like to have them as separate images we can even run ksamplers on with different prompts.

ControlNet Inpaint (And other) + Tiled Diffusion Error

I dont know why, but this happen all the time, when the image is bigger then the tile_width + tile_height.

But i need Control Net for my Workflow...

Please any idea ?

Simple Upscale example workflow produces jumbled images

I loaded the example Simple Upscale workflow from the readme, but get some strange results, no matter what checkpoint I use.

Here's the base image it makes, which looks good enough to me, though different than your example despite using the same checkpoint:

However, after upscale, it becomes this:

I'm using the same ControlNet model, and checkpoint. I touched nothing else. The 4x Upscale example seems to work fine.

IMPORT FAILED after update

Fails to import after 6685bd2
python: 3.10.13 torch: 1.13.0+rocm5.2

Traceback (most recent call last):
  File "/sd/ComfyUI/nodes.py", line 1872, in load_custom_node
    module_spec.loader.exec_module(module)
  File "<frozen importlib._bootstrap_external>", line 883, in exec_module
  File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
  File "/sd/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/__init__.py", line 1, in <module>
    from .tiled_diffusion import NODE_CLASS_MAPPINGS as TD_NCM, NODE_DISPLAY_NAME_MAPPINGS as TD_NDCM
  File "/sd/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/tiled_diffusion.py", line 494, in <module>
    hook_all()
  File "/sd/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/utils.py", line 69, in hook_all
    hook_calc_cond_uncond_batch()
  File "/sd/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/utils.py", line 34, in hook_calc_cond_uncond_batch
    calc_cond_uncond_batch = getattr(sys.modules[m], 'calc_cond_uncond_batch')
AttributeError: module 'impact.special_samplers' has no attribute 'calc_cond_uncond_batch'

Cannot import /sd/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion module for custom nodes: module 'impact.special_samplers' has no attribute 'calc_cond_uncond_batch'

It is best to get a matching set of inversion noise that cannot be used by others, Or give an example of inverting noise with a custom node

Custom nodes can invert noise, but the sampler cannot remove the inversion noise. The purpose of adding inverse noise is to mix some noise of the original image together and then sample them together to achieve the purpose of removing the original noise. However, unsampler and custom sampler It bothered me for a long time, it can't be as simple as a1111. Please give an example of how a custom node can invert noise and use sampling to eliminate original noise. I think many people are troubled by this problem like me.

Using the example Simple and 4x Upscale workflows results in an error when using SDXL

I feel like I must be doing something wrong since no one else is encountering this. I tried to look for any special settings I must add/change to use SDXL, but nothing was mentioned in the readme. This occurs when using either the Simple Upscale or 4x Upscale workflow examples in the readme.

Here's an example, where you can turn on/off Simple or 4x:

UpscaleSimpleAnd4x.json

Hook up an SDXL model/latent, set to 1024x1024.
Change the Upscale Image node to 2048x2048, following the example upscale amount in the original workflow (included this in case it's necessary for it to work properly, even though the bug happens without this step).
Click on Queue to generate.

Instead of completing the upscale, it results in this error:

Error occurred when executing KSamplerAdvanced:

mat1 and mat2 shapes cannot be multiplied (385x2048 and 768x320)

File "Q:\SD\ComfyUI\Portable\ComfyUI\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\nodes.py", line 1389, in sample
return common_ksampler(model, noise_seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise, disable_noise=disable_noise, start_step=start_at_step, last_step=end_at_step, force_full_denoise=force_full_denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\nodes.py", line 1325, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 22, in informative_sample
raise e
File "Q:\SD\ComfyUI\Portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 9, in informative_sample
return original_sample(*args, **kwargs) # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations.
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 241, in motion_sample
return orig_comfy_sample(model, noise, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\sample.py", line 100, in sample
samples = sampler.sample(noise, positive_copy, negative_copy, 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 "Q:\SD\ComfyUI\Portable\ComfyUI\custom_nodes\ComfyUI_smZNodes_init_.py", line 130, in KSampler_sample
return KSampler_sample(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\samplers.py", line 716, 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 "Q:\SD\ComfyUI\Portable\ComfyUI\custom_nodes\ComfyUI_smZNodes_init.py", line 149, in sample
return _sample(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\samplers.py", line 622, in sample
samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\samplers.py", line 561, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\k_diffusion\sampling.py", line 503, in sample_dpmpp_2s_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\samplers.py", line 285, in forward
out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self.call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\samplers.py", line 275, in forward
return self.apply_model(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\custom_nodes\ComfyUI_smZNodes\smZNodes.py", line 1030, in apply_model
out = super().apply_model(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\samplers.py", line 272, in apply_model
out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\samplers.py", line 252, in sampling_function
cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond, x, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion.patches.py", line 95, 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 "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion\tiled_diffusion.py", line 528, in call
c_tile['control'] = control.get_control(x_tile, t_tile, c_tile, len(cond_or_uncond))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\controlnet.py", line 176, in get_control
control = self.control_model(x=x_noisy.to(dtype), hint=self.cond_hint, timesteps=timestep.float(), context=context.to(dtype), y=y)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\cldm\cldm.py", line 305, in forward
h = module(h, emb, context)
^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 62, in forward
return forward_timestep_embed(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 46, in forward_timestep_embed
x = layer(x, context, transformer_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\ldm\modules\attention.py", line 616, in forward
x = block(x, context=context[i], transformer_options=transformer_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\ldm\modules\attention.py", line 443, in forward
return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\ldm\modules\diffusionmodules\util.py", line 189, in checkpoint
return func(*inputs)
^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\ldm\modules\attention.py", line 543, in _forward
n = self.attn2(n, context=context_attn2, value=value_attn2)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\ldm\modules\attention.py", line 387, in forward
k = self.to_k(context)
^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\ComfyUI\comfy\ops.py", line 27, in forward
return super().forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "Q:\SD\ComfyUI\Portable\python_embeded\Lib\site-packages\torch\nn\modules\linear.py", line 114, in forward
return F.linear(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

dont work anymore

!!! Exception during processing !!! Traceback (most recent call last): File "E:\SD\ComfyUI_port_2\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\nodes.py", line 1403, in sample return common_ksampler(model, noise_seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise, disable_noise=disable_noise, start_step=start_at_step, last_step=end_at_step, force_full_denoise=force_full_denoise) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\nodes.py", line 1339, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 9, in informative_sample return original_sample(*args, **kwargs) # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\comfy\sample.py", line 100, in sample samples = sampler.sample(noise, positive_copy, negative_copy, 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 "E:\SD\ComfyUI_port_2\ComfyUI\comfy\samplers.py", line 702, 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 "E:\SD\ComfyUI_port_2\ComfyUI\comfy\samplers.py", line 607, in sample samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\comfy\samplers.py", line 545, in sample samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\python_embeded\Lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\comfy\k_diffusion\sampling.py", line 503, in sample_dpmpp_2s_ancestral denoised = model(x, sigmas[i] * s_in, **extra_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\comfy\samplers.py", line 283, in forward out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\comfy\samplers.py", line 270, in forward return self.apply_model(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\comfy\samplers.py", line 267, in apply_model out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\comfy\samplers.py", line 244, in sampling_function out = calc_cond_batch(model, conds, x, timestep, model_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\comfy\samplers.py", line 215, 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 "E:\SD\ComfyUI_port_2\python_embeded\Lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "E:\SD\ComfyUI_port_2\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion\tiled_diffusion.py", line 546, in __call__ self.process_controlnet(x_tile.shape, x_tile.dtype, c_in, cond_or_uncond, bboxes, N, batch_id) File "E:\SD\ComfyUI_port_2\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion\tiled_diffusion.py", line 328, in process_controlnet if (PH, PW) == (control.cond_hint_original.shape[-2], control.cond_hint_original.shape[-1]): ^^^^^^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'dict' object has no attribute 'cond_hint_original'

Something wrong with my Ksampler.

Error occurred when executing KSampler:

shape '[6, -1, 10, 64]' is invalid for input of size 10240

File "/mnt/drive0/AIGC/ComfyUI/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/nodes.py", line 1369, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/nodes.py", line 1339, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/sampling.py", line 248, in motion_sample
return orig_comfy_sample(model, noise, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/sample_error_enhancer.py", line 22, in informative_sample
raise e
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/sample_error_enhancer.py", line 9, in informative_sample
return original_sample(*args, **kwargs) # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations.
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-Advanced-ControlNet/adv_control/control_reference.py", line 46, in refcn_sample
return orig_comfy_sample(model, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/sample.py", line 100, in sample
samples = sampler.sample(noise, positive_copy, negative_copy, 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 "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI_smZNodes/smZNodes.py", line 1380, in KSampler_sample
return _KSampler_sample(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/samplers.py", line 705, 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 "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI_smZNodes/smZNodes.py", line 1399, in sample
return _sample(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/samplers.py", line 610, in sample
samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/samplers.py", line 548, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/k_diffusion/sampling.py", line 137, in sample_euler
denoised = model(x, sigma_hat * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/samplers.py", line 286, in forward
out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self.call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/samplers.py", line 273, in forward
return self.apply_model(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI_smZNodes/smZNodes.py", line 1012, in apply_model
out = super().apply_model(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/samplers.py", line 270, in apply_model
out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/samplers.py", line 250, in sampling_function
cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond, x, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/.patches.py", line 96, 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 "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/tiled_diffusion.py", line 418, in call
c_tile['control'] = control.get_control(x_tile, ts_tile, c_tile, len(cond_or_uncond))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/controlnet.py", line 463, in get_control
control_prev = self.previous_controlnet.get_control(x_noisy, t, cond, batched_number)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-Advanced-ControlNet/adv_control/utils.py", line 549, in get_control_inject
return self.get_control_advanced(x_noisy, t, cond, batched_number)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-Advanced-ControlNet/adv_control/control.py", line 32, in get_control_advanced
return self.sliding_get_control(x_noisy, t, cond, batched_number)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-Advanced-ControlNet/adv_control/control.py", line 78, in sliding_get_control
control = self.control_model(x=x_noisy.to(dtype), hint=self.cond_hint, timesteps=timestep.float(), context=context.to(dtype), y=y)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/cldm/cldm.py", line 305, in forward
h = module(h, emb, context)
^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/ldm/modules/diffusionmodules/openaimodel.py", line 60, in forward
return forward_timestep_embed(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/ldm/modules/diffusionmodules/openaimodel.py", line 44, in forward_timestep_embed
x = layer(x, context, transformer_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/ldm/modules/attention.py", line 633, in forward
x = block(x, context=context[i], transformer_options=transformer_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-layerdiffuse/lib_layerdiffusion/attention_sharing.py", line 253, in forward
return func(self, x, context, transformer_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/custom_nodes/ComfyUI-Easy-Use/py/layer_diffuse/attension_sharing.py", line 253, in forward
return func(self, x, context, transformer_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/ldm/modules/attention.py", line 460, in forward
return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/ldm/modules/diffusionmodules/util.py", line 191, in checkpoint
return func(*inputs)
^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/ldm/modules/attention.py", line 560, in _forward
n = self.attn2(n, context=context_attn2, value=value_attn2)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI_ENV/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/ldm/modules/attention.py", line 412, in forward
out = optimized_attention(q, k, v, self.heads)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/ldm/modules/attention.py", line 340, in attention_pytorch
q, k, v = map(
^^^^^^^
File "/mnt/drive0/AIGC/ComfyUI/comfy/ldm/modules/attention.py", line 341, in
lambda t: t.view(b, -1, heads, dim_head).transpose(1, 2),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Excuse me, I cannot find an option similar to the magnification factor in the existing node

Excuse me, I cannot find an option similar to the magnification factor in the existing node. How can I enlarge the resolution of the image? Thank you so much!

Tiled VAE RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

I use IP-Adapter in my workflow. when running to the Tiled VAE node, it displays the
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
But when I replace it with the original VAE decoding node, the problem is solved.

Impact FaceDetailer Compatibility Issue

Currently getting this when trying to use bbox guide_size in Impact Pack's ddetailer node:

Error occurred when executing FaceDetailer:

shape '[1, 13, 10]' is invalid for input of size 144

File "/workspace/ComfyUI/execution.py", line 154, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/workspace/ComfyUI/execution.py", line 84, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/workspace/ComfyUI/execution.py", line 77, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/workspace/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 489, in doit
enhanced_img, cropped_enhanced, cropped_enhanced_alpha, mask, cnet_pil_list = FaceDetailer.enhance_face(
File "/workspace/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 446, in enhance_face
DetailerForEach.do_detail(image, segs, model, clip, vae, guide_size, guide_size_for_bbox, max_size, seed, steps, cfg,
File "/workspace/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 237, in do_detail
enhanced_image, cnet_pils = core.enhance_detail(cropped_image, model, clip, vae, guide_size, guide_size_for_bbox, max_size,
File "/workspace/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 290, in enhance_detail
refined_latent = ksampler_wrapper(model2, seed2, steps2, cfg2, sampler_name2, scheduler2, positive2, negative2,
File "/workspace/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 75, in ksampler_wrapper
nodes.KSampler().sample(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "/workspace/ComfyUI/nodes.py", line 1299, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "/workspace/ComfyUI/nodes.py", line 1269, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "/workspace/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/sample_error_enhancer.py", line 22, in informative_sample
raise e
File "/workspace/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/sample_error_enhancer.py", line 9, in informative_sample
return original_sample(*args, **kwargs) # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations.
File "/workspace/ComfyUI/comfy/sample.py", line 101, in sample
samples = sampler.sample(noise, positive_copy, negative_copy, 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 "/workspace/ComfyUI/comfy/samplers.py", line 716, 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 "/workspace/ComfyUI/comfy/samplers.py", line 622, in sample
samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
File "/workspace/ComfyUI/comfy/samplers.py", line 561, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
File "/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/workspace/ComfyUI/comfy/k_diffusion/sampling.py", line 137, in sample_euler
denoised = model(x, sigma_hat * s_in, **extra_args)
File "/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/workspace/ComfyUI/comfy/samplers.py", line 285, in forward
out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed)
File "/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/workspace/ComfyUI/comfy/samplers.py", line 275, in forward
return self.apply_model(*args, **kwargs)
File "/workspace/ComfyUI/comfy/samplers.py", line 272, in apply_model
out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed)
File "/workspace/ComfyUI/comfy/samplers.py", line 263, in sampling_function
cfg_result = fn(args)
File "/workspace/ComfyUI/comfy_extras/nodes_sag.py", line 148, in post_cfg_function
degraded = create_blur_map(uncond_pred, uncond_attn, sag_sigma, sag_threshold)
File "/workspace/ComfyUI/comfy_extras/nodes_sag.py", line 66, in create_blur_map
mask.reshape(b, *mid_shape)

Using default tiled diffusion settings (768 x 768, 64 overlap, 4 batch size).

Very Nice !

Would it be possible to support https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet .

Its the only repo for controlnets are is done properly like Auto1111. (It has control of the controlnet injected weights, aka, 'my prompt/balanced/etc)

Which is pretty key for upscaling work with MultiDiffusion.

Nice work on this !

Noise invertion

Hello, first of great work, that it took this long to get the plugin ported to comfyui is crazy,
Any update on the progress on noise invention in the original automatic1111 plugin?

warning control could not be applied torch.Size([6, 320, 24, 24]) torch.Size([6, 320, 48, 48])

I am using example workflow of Tiled Diffusion ComfyUI. When i run workflow i am getting this warning message. And i think control net tile doesn't work correctly.

warning control could not be applied torch.Size([6, 320, 24, 24]) torch.Size([6, 320, 48, 48])

idea / feature request: for multiple scaling stages - possible to stay in latent space?

Thank you for your work, these are great upscaling nodes

I found that using two stages of 2x worked better than one pass with 4x upsampling. Then I found that using mixture of diffusers first at 2x followed by multi-diffusion at 2x gave improved details. At least that was my experience so far.

However, in staged use, one must decode, then encode the latent which costs time and perhaps some quality loss in converting from latent to pixels space multiple times. Is it possible to go from one stage to the next staying in the latent space? Perhaps if the tile size is kept the same?

Even better would be an iterative cycle setting - to allow users to set the final magnification and have the nodes run as many cycles as needed.

Control Net and Tiled Diffusion Error

Good Day.

If i try to add any control net i got this error:

This is the part of my workflow:

Any Idea ?

Import failed

[RuntimeError: Size of tensors... & Input and output sizes... ].

When using Tiled Diffusion together with ControlNet (advanced) and preprocessor, there is an error that I can't figure out. Do the options of this node need to be adjusted accordingly so that the values are read correctly? Is the preprocessor resolution somehow being passed to ControlNet and then to KSampler and causing a conflict with Tiled node?

Full error logs:
Whenever "tile_batch_size" is set to more than 1 and a preprocessed image (for example LineArt preprocessor) enters ControlNet as input image, this error pops up.

RuntimeError: Sizes of tensors must match except in dimension 0.
Sizes of tensors.txt

"Tile_batch_size" = 1, input Controlnet from preprocessor. Same story. 👇🏻

RuntimeError: Input and output sizes should be greater than 0, but got input (H: 0, W: 0) output (H: 544, W: 960)
Input & output.txt

Bug when using with controlnet

Hi, when using tiled diffusion with more than one controlnet in series, I was running into errors. The workflow is here:
https://github.com/aravindhv10/ComfyUI-TiledDiffusion/blob/fix_controlnet/counter_example.json

The exact error is:

Requested to load ControlNet
Requested to load SDXL
Loading 3 new models
  0%|                                                                                                                         | 0/4 [00:07<?, ?it/s]
!!! Exception during processing !!!
Traceback (most recent call last):
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/execution.py", line 151, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/execution.py", line 81, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/execution.py", line 74, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/nodes.py", line 1344, in sample
    return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/nodes.py", line 1314, in common_ksampler
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/sample_error_enhancer.py", line 9, in informative
    return original_sample(*args, **kwargs)  # This code helps interpret error messages that occur within exceptions but does not have any impact on
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/custom_nodes/ComfyUI-Advanced-ControlNet/adv_control/control_reference.py", line 47, in refcn_sam
    return orig_comfy_sample(model, *args, **kwargs)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/sample.py", line 37, in sample
    samples = sampler.sample(noise, positive, negative, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_d
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/samplers.py", line 755, 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 "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/samplers.py", line 657, in sample
    return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/samplers.py", line 644, in sample
    output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/samplers.py", line 623, in inner_sample
    samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/samplers.py", line 534, in sample
    samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
  File "/home/ubuntu/dbnew/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/k_diffusion/sampling.py", line 539, in sample_dpmpp_sde
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/samplers.py", line 272, in __call__
    out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/samplers.py", line 610, in __call__
    return self.predict_noise(*args, **kwargs)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/samplers.py", line 613, 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 "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/comfy/samplers.py", line 258, in sampling_function
    out = calc_cond_batch(model, conds, x, timestep, model_options)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/.patches.py", line 89, 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 "/home/ubuntu/dbnew/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/tiled_diffusion.py", line 546, in __call__
    self.process_controlnet(x_tile.shape, x_tile.dtype, c_in, cond_or_uncond, bboxes, N, batch_id)
  File "/home/ubuntu/GITHUB/comfyanonymous/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/tiled_diffusion.py", line 342, in process_controlnet
    self.control_params[tuple_key][param_id][batch_id]=control.cond_hint
IndexError: list assignment index out of range

It seems that self.control_params (https://github.com/shiimizu/ComfyUI-TiledDiffusion/blob/main/tiled_diffusion.py#L292) in some circumstances is not initialized properly.
I found a hacky way to fix this:
https://github.com/aravindhv10/ComfyUI-TiledDiffusion/blob/fix_controlnet/tiled_diffusion.py#L308-L314
wanted to know if this could be merged or there was a better way?
Perhaps, these lines:
https://github.com/shiimizu/ComfyUI-TiledDiffusion/blob/main/tiled_diffusion.py#L303-L306
can be rewritten.

Thanks!

Second Tiled Diffusion run in the workflow:

ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/execution.py", line 152, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/execution.py", line 82, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/custom_nodes/ComfyUI-0246/utils.py", line 373, in new_func
    res_value = old_func(*final_args, **kwargs)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/execution.py", line 75, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/nodes.py", line 1375, in sample
    return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/nodes.py", line 1345, in common_ksampler
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/sampling.py", line 241, in motion_sample
    return orig_comfy_sample(model, noise, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/sample_error_enhancer.py", line 9, in informative_sample
    return original_sample(*args, **kwargs)  # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations.
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/sample.py", line 100, in sample
    samples = sampler.sample(noise, positive_copy, negative_copy, 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 "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/custom_nodes/ComfyUI_smZNodes/__init__.py", line 130, in KSampler_sample
    return _KSampler_sample(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/samplers.py", line 712, 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 "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/custom_nodes/ComfyUI_smZNodes/__init__.py", line 149, in sample
    return _sample(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/samplers.py", line 618, in sample
    samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/samplers.py", line 557, in sample
    samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jeff/.virtualenvs/comfyui/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/k_diffusion/sampling.py", line 701, in sample_dpmpp_2m_sde_gpu
    return sample_dpmpp_2m_sde(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, eta=eta, s_noise=s_noise, noise_sampler=noise_sampler, solver_type=solver_type)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jeff/.virtualenvs/comfyui/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/k_diffusion/sampling.py", line 613, in sample_dpmpp_2m_sde
    denoised = model(x, sigmas[i] * s_in, **extra_args)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jeff/.virtualenvs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jeff/.virtualenvs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/samplers.py", line 281, in forward
    out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jeff/.virtualenvs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/jeff/.virtualenvs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/samplers.py", line 271, in forward
    return self.apply_model(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/custom_nodes/ComfyUI_smZNodes/smZNodes.py", line 1030, in apply_model
    out = super().apply_model(*args, **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/samplers.py", line 268, in apply_model
    out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/samplers.py", line 248, in sampling_function
    cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond_, x, timestep, model_options)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/comfy/samplers.py", line 220, 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 "/home/jeff/.virtualenvs/comfyui/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/net/dj/code/clones/github.com/comfyanonymous/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/tiled_diffusion.py", line 528, in __call__
    c_tile['control'] = control.get_control(x_tile, t_tile, c_tile, len(cond_or_uncond))
                        ^^^^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'get_control'

When we go to the second Tiled Diffusion run in the same workflow, using the latest HEAD which is ec40acf

Import failed

I am on the portable version on Windows 11, and ComfyUI is fully updated.

The error in the terminal:

Traceback (most recent call last):
File "F:\Stable-Diffusion\ComfyUI\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1872, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 940, in exec_module
File "", line 241, in call_with_frames_removed
File "F:\Stable-Diffusion\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion_init.py", line 1, in
from .tiled_diffusion import NODE_CLASS_MAPPINGS as TD_NCM, NODE_DISPLAY_NAME_MAPPINGS as TD_NDCM
File "F:\Stable-Diffusion\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion\tiled_diffusion.py", line 304
>>>>>>> 195fed5
^
SyntaxError: invalid decimal literal

Cannot import F:\Stable-Diffusion\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion module for custom nodes: invalid decimal literal (tiled_diffusion.py, line 304)

Incompatible with new RefCN functionality in ComfyUI-Advanced-ControlNet

Probably a "not your bug" bug, but opening here for awareness/tracking purposes, and in case there's something that can be done on this side to mitigate the issue. Kosinkadink wrote on Discord:

ref cn will not work with tiled diffusion at this time
the cn would need to have access to a vae during sampling to encode the input image per tile, and currently it prepares them beforehand. i'll eventually refactor code to make it compatible with existing tiling solutions, but for the time being i don't want to introduce potential memory usage issues without putting in the proper time to investigate

~~Should probably make a corresponding issue on ComfyUI-Advanced-ControlNet. I'll update here if I do that.~~ See also Kosinkadink/ComfyUI-Advanced-ControlNet#96