ComfyUI-AnimateDiff-Evolved: Error occurred when executing KSampler: cat() received an invalid combination of arguments - got (Tensor, int), but expected one of:

Greetings @Kosinkadink

I’ve been trying to get this node to work but have been running into an error I do not particular understand. The following error occurs when I try and run the workflow you provided here but I keep running into the following error. Everything appears to be installed correctly and the KSampler works fine for image generation so I’m not sure what’s going on. Let me know if you can provide any additional info. I’m running comfyui via a docker container in wsl2(https://github.com/AbdBarho/stable-diffusion-webui-docker).

Error occurred when executing KSampler:

cat() received an invalid combination of arguments - got (Tensor, int), but expected one of:
* (tuple of Tensors tensors, int dim, *, Tensor out)
* (tuple of Tensors tensors, name dim, *, Tensor out)


File "/stable-diffusion/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/stable-diffusion/execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/stable-diffusion/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/stable-diffusion/nodes.py", line 1211, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "/stable-diffusion/nodes.py", line 1181, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "/stable-diffusion/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/sampling.py", line 161, in animatediff_sample
return wrap_function_to_inject_xformers_bug_info(orig_comfy_sample)(model, *args, **kwargs)
File "/stable-diffusion/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/model_utils.py", line 144, in wrapped_function
return function_to_wrap(*args, **kwargs)
File "/stable-diffusion/comfy/sample.py", line 95, 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 "/stable-diffusion/comfy/samplers.py", line 733, in sample
samples = getattr(k_diffusion_sampling, "sample_{}".format(self.sampler))(self.model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar)
File "/opt/conda/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/stable-diffusion/comfy/k_diffusion/sampling.py", line 137, in sample_euler
denoised = model(x, sigma_hat * s_in, **extra_args)
File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/stable-diffusion/comfy/samplers.py", line 323, in forward
out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, cond_concat=cond_concat, model_options=model_options, seed=seed)
File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/stable-diffusion/comfy/k_diffusion/external.py", line 125, in forward
eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
File "/stable-diffusion/comfy/k_diffusion/external.py", line 151, in get_eps
return self.inner_model.apply_model(*args, **kwargs)
File "/stable-diffusion/comfy/samplers.py", line 311, in apply_model
out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, cond_concat, model_options=model_options, seed=seed)
File "/stable-diffusion/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/sampling.py", line 527, in sliding_sampling_function
cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, cond_concat, model_options)
File "/stable-diffusion/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/sampling.py", line 427, in calc_cond_uncond_batch
output = model_function(input_x, timestep_, **c).chunk(batch_chunks)
File "/stable-diffusion/comfy/model_base.py", line 56, in apply_model
context = torch.cat(c_crossattn, 1)

About this issue

Original URL
State: closed
Created 9 months ago
Reactions: 2
Comments: 16 (9 by maintainers)

Most upvoted comments

Yeah I haven’t changed anything from your original workflow since I’m just trying to confirm that everything is installed properly. Clearly it is not.

As of right now I’m installing the custom node via the docker file.

WORKDIR ${ROOT}/custom_nodes/
RUN --mount=type=cache,target=/root/.cache/pip \
  git clone https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved.git

Then I add the models to the appropriate directory and they seem to appear no problem.

This how it the WF looks after the failure:

full log:

webui-docker-comfy-1  | got prompt
webui-docker-comfy-1  | 2
webui-docker-comfy-1  | 2
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
webui-docker-comfy-1  | Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
webui-docker-comfy-1  | model_type EPS
webui-docker-comfy-1  | adm 0
webui-docker-comfy-1  | making attention of type 'vanilla-xformers' with 512 in_channels
webui-docker-comfy-1  | building MemoryEfficientAttnBlock with 512 in_channels...
webui-docker-comfy-1  | Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
webui-docker-comfy-1  | making attention of type 'vanilla-xformers' with 512 in_channels
webui-docker-comfy-1  | building MemoryEfficientAttnBlock with 512 in_channels...
webui-docker-comfy-1  | missing {'cond_stage_model.logit_scale', 'cond_stage_model.text_projection'}
webui-docker-comfy-1  | left over keys: dict_keys(['cond_stage_model.transformer.text_model.embeddings.position_ids'])
webui-docker-comfy-1  | [AnimateDiffEvo] - INFO - Loading motion module mm_sd_v14.ckpt
webui-docker-comfy-1  | [AnimateDiffEvo] - INFO - Using fp16, converting motion module to fp16
webui-docker-comfy-1  | loading new
webui-docker-comfy-1  | [AnimateDiffEvo] - INFO - Regular AnimateDiff activated - latents passed in (16) less or equal to context_length None.
webui-docker-comfy-1  | [AnimateDiffEvo] - INFO - Injecting motion module mm_sd_v14.ckpt version v1.
webui-docker-comfy-1  | loading new
  0% 0/20 [00:00<?, ?it/s]
  0% 0/20 [00:00<?, ?it/s]
webui-docker-comfy-1  | [AnimateDiffEvo] - INFO - Ejecting motion module mm_sd_v14.ckpt version v1.
webui-docker-comfy-1  | [AnimateDiffEvo] - INFO - Cleaning motion module from unet.
webui-docker-comfy-1  | /stable-diffusion/comfy/model_base.py:47: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
webui-docker-comfy-1  |   self.register_buffer('betas', torch.tensor(betas, dtype=torch.float32))
webui-docker-comfy-1  | /stable-diffusion/comfy/model_base.py:48: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
webui-docker-comfy-1  |   self.register_buffer('alphas_cumprod', torch.tensor(alphas_cumprod, dtype=torch.float32))
webui-docker-comfy-1  | !!! Exception during processing !!!
webui-docker-comfy-1  | Traceback (most recent call last):
webui-docker-comfy-1  |   File "/stable-diffusion/execution.py", line 151, in recursive_execute
webui-docker-comfy-1  |     output_data, output_ui = get_output_data(obj, input_data_all)
webui-docker-comfy-1  |   File "/stable-diffusion/execution.py", line 81, in get_output_data
webui-docker-comfy-1  |     return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
webui-docker-comfy-1  |   File "/stable-diffusion/execution.py", line 74, in map_node_over_list
webui-docker-comfy-1  |     results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
webui-docker-comfy-1  |   File "/stable-diffusion/nodes.py", line 1211, in sample
webui-docker-comfy-1  |     return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
webui-docker-comfy-1  |   File "/stable-diffusion/nodes.py", line 1181, in common_ksampler
webui-docker-comfy-1  |     samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
webui-docker-comfy-1  |   File "/stable-diffusion/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/sampling.py", line 161, in animatediff_sample
webui-docker-comfy-1  |     return wrap_function_to_inject_xformers_bug_info(orig_comfy_sample)(model, *args, **kwargs)
webui-docker-comfy-1  |   File "/stable-diffusion/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/model_utils.py", line 144, in wrapped_function
webui-docker-comfy-1  |     return function_to_wrap(*args, **kwargs)
webui-docker-comfy-1  |   File "/stable-diffusion/comfy/sample.py", line 95, in sample
webui-docker-comfy-1  |     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)
webui-docker-comfy-1  |   File "/stable-diffusion/comfy/samplers.py", line 733, in sample
webui-docker-comfy-1  |     samples = getattr(k_diffusion_sampling, "sample_{}".format(self.sampler))(self.model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar)
webui-docker-comfy-1  |   File "/opt/conda/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
webui-docker-comfy-1  |     return func(*args, **kwargs)
webui-docker-comfy-1  |   File "/stable-diffusion/comfy/k_diffusion/sampling.py", line 137, in sample_euler
webui-docker-comfy-1  |     denoised = model(x, sigma_hat * s_in, **extra_args)
webui-docker-comfy-1  |   File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
webui-docker-comfy-1  |     return forward_call(*args, **kwargs)
webui-docker-comfy-1  |   File "/stable-diffusion/comfy/samplers.py", line 323, in forward
webui-docker-comfy-1  |     out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, cond_concat=cond_concat, model_options=model_options, seed=seed)
webui-docker-comfy-1  |   File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
webui-docker-comfy-1  |     return forward_call(*args, **kwargs)
webui-docker-comfy-1  |   File "/stable-diffusion/comfy/k_diffusion/external.py", line 125, in forward
webui-docker-comfy-1  |     eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
webui-docker-comfy-1  |   File "/stable-diffusion/comfy/k_diffusion/external.py", line 151, in get_eps
webui-docker-comfy-1  |     return self.inner_model.apply_model(*args, **kwargs)
webui-docker-comfy-1  |   File "/stable-diffusion/comfy/samplers.py", line 311, in apply_model
webui-docker-comfy-1  |     out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, cond_concat, model_options=model_options, seed=seed)
webui-docker-comfy-1  |   File "/stable-diffusion/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/sampling.py", line 527, in sliding_sampling_function
webui-docker-comfy-1  |     cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, cond_concat, model_options)
webui-docker-comfy-1  |   File "/stable-diffusion/custom_nodes/ComfyUI-AnimateDiff-Evolved/animatediff/sampling.py", line 427, in calc_cond_uncond_batch
webui-docker-comfy-1  |     output = model_function(input_x, timestep_, **c).chunk(batch_chunks)
webui-docker-comfy-1  |   File "/stable-diffusion/comfy/model_base.py", line 56, in apply_model
webui-docker-comfy-1  |     context = torch.cat(c_crossattn, 1)
webui-docker-comfy-1  | TypeError: cat() received an invalid combination of arguments - got (Tensor, int), but expected one of:
webui-docker-comfy-1  |  * (tuple of Tensors tensors, int dim, *, Tensor out)
webui-docker-comfy-1  |  * (tuple of Tensors tensors, name dim, *, Tensor out)
webui-docker-comfy-1  |
webui-docker-comfy-1  |
webui-docker-comfy-1  | Prompt executed in 12.32 seconds

thepromptengineer on Sep 25, 2023

@Kosinkadink thanks boss. yeah that was it. sorry for the oversight and thank you for the breadcrumbs. I think @nov1ce1762 problem is the same, old portable comfyui. Feel free to close the issue or leave it for people looking to troubleshoot this in the future.

thepromptengineer on Sep 26, 2023