RuntimeError: input must be 4-dimensional (new sd-video related)

[patientx]

System : ryzen 3600 - rx 6600 8 GB - Windows 10 - Latest comfyui

Using the sample workflow on the blog (https://comfyanonymous.github.io/ComfyUI_examples/video/) I try generating with the new
svd model, I always get this error :

ERROR:root:!!! Exception during processing !!! ERROR:root:Traceback (most recent call last): File "D:\ComfyUI\execution.py", line 153, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "D:\ComfyUI\execution.py", line 83, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "D:\ComfyUI\execution.py", line 76, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "D:\ComfyUI\nodes.py", line 1286, in sample return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise) File "D:\ComfyUI\nodes.py", line 1256, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 22, in informative_sample raise e File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 9, in informative_sample return original_sample(*args, **kwargs) File "D:\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 173, in animatediff_sample return orig_comfy_sample(model, noise, *args, **kwargs) File "D:\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 "D:\ComfyUI\comfy\samplers.py", line 711, 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 "D:\ComfyUI\comfy\samplers.py", line 617, in sample samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) File "D:\ComfyUI\comfy\samplers.py", line 556, in sample samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options) File "D:\ComfyUI\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "D:\ComfyUI\comfy\k_diffusion\sampling.py", line 137, in sample_euler denoised = model(x, sigma_hat * s_in, **extra_args) File "D:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "D:\ComfyUI\comfy\samplers.py", line 277, in forward out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed) File "D:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "D:\ComfyUI\comfy\samplers.py", line 267, in forward return self.apply_model(*args, **kwargs) File "D:\ComfyUI\comfy\samplers.py", line 264, in apply_model out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed) File "D:\ComfyUI\comfy\samplers.py", line 252, in sampling_function cond, uncond = calc_cond_uncond_batch(model, cond, uncond, x, timestep, model_options) File "D:\ComfyUI\comfy\samplers.py", line 230, in calc_cond_uncond_batch output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks) File "D:\ComfyUI\comfy\model_base.py", line 73, in apply_model model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float() File "D:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "D:\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 854, 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 "D:\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 38, in forward_timestep_embed x = layer(x, emb, num_video_frames, image_only_indicator) File "D:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "D:\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 340, in forward x = self.time_stack( File "D:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "D:\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 232, in forward return checkpoint( File "D:\ComfyUI\comfy\ldm\modules\diffusionmodules\util.py", line 190, in checkpoint return func(*inputs) File "D:\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 245, in _forward h = self.in_layers(x) File "D:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "D:\ComfyUI\venv\lib\site-packages\torch\nn\modules\container.py", line 217, in forward input = module(input) File "D:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "D:\ComfyUI\venv\lib\site-packages\torch\nn\modules\conv.py", line 613, in forward return self._conv_forward(input, self.weight, self.bias) File "D:\ComfyUI\venv\lib\site-packages\torch\nn\modules\conv.py", line 608, in _conv_forward return F.conv3d( RuntimeError: input must be 4-dimensional

Couldn't find any mention of it here.

[ibaraki-douji]

Hey, i got the same issue.

• R7 5700
• RX 6700
• Win 11

my guess is that amd gpu (and windows only so maybe directml) can't gen for now because removing the directml option to take my nvidia worked just fine as well as cpu.

[patientx]

Hey, i got the same issue.

• R7 5700
• RX 6700
• Win 11

my guess is that amd gpu (and windows only so maybe directml) can't gen for now because removing the directml option to take my nvidia worked just fine as well as cpu.

thanks for trying, at least we know now ...

[silentoplayz]

I also have this issue.

• Windows 11 Pro 22H2
• OS Build 22621.2715
• Windows Feature Experience Pack 1000.22677.1000.0
• RX 6800 XT

Error occurred when executing KSampler:
input must be 4-dimensional
  File "X:\ComfyUI\ComfyUI\execution.py", line 153, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
  File "X:\ComfyUI\ComfyUI\execution.py", line 83, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
  File "X:\ComfyUI\ComfyUI\execution.py", line 76, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
  File "X:\ComfyUI\ComfyUI\nodes.py", line 1299, in sample
    return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
  File "X:\ComfyUI\ComfyUI\nodes.py", line 1269, in common_ksampler
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
  File "X:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 22, in informative_sample
    raise e
  File "X:\ComfyUI\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 "X:\ComfyUI\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 "X:\ComfyUI\ComfyUI\comfy\samplers.py", line 711, 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 "X:\ComfyUI\ComfyUI\comfy\samplers.py", line 617, in sample
    samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
  File "X:\ComfyUI\ComfyUI\comfy\samplers.py", line 556, 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:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "X:\ComfyUI\ComfyUI\comfy\k_diffusion\sampling.py", line 745, in sample_lcm
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "C:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "X:\ComfyUI\ComfyUI\comfy\samplers.py", line 277, in forward
    out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed)
  File "C:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "X:\ComfyUI\ComfyUI\comfy\samplers.py", line 267, in forward
    return self.apply_model(*args, **kwargs)
  File "X:\ComfyUI\ComfyUI\comfy\samplers.py", line 264, in apply_model
    out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed)
  File "X:\ComfyUI\ComfyUI\comfy\samplers.py", line 252, in sampling_function
    cond, uncond = calc_cond_uncond_batch(model, cond, uncond, x, timestep, model_options)
  File "X:\ComfyUI\ComfyUI\comfy\samplers.py", line 230, in calc_cond_uncond_batch
    output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
  File "X:\ComfyUI\ComfyUI\comfy\model_base.py", line 73, in apply_model
    model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
  File "C:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "X:\ComfyUI\ComfyUI\custom_nodes\SeargeSDXL\modules\custom_sdxl_ksampler.py", line 70, in new_unet_forward
    x0 = old_unet_forward(self, x, timesteps, context, y, control, transformer_options, **kwargs)
  File "X:\ComfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 855, 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 "X:\ComfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 38, in forward_timestep_embed
    x = layer(x, emb, num_video_frames, image_only_indicator)
  File "C:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "X:\ComfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 341, in forward
    x = self.time_stack(
  File "C:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "X:\ComfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 233, in forward
    return checkpoint(
  File "X:\ComfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\util.py", line 190, in checkpoint
    return func(*inputs)
  File "X:\ComfyUI\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 246, in _forward
    h = self.in_layers(x)
  File "C:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\container.py", line 217, in forward
    input = module(input)
  File "C:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\conv.py", line 613, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "C:\Users\G30\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\conv.py", line 608, in _conv_forward
    return F.conv3d(

This too happens when I try to generate a video from an image using the sample workflow on the ComfyUI blog. https://comfyanonymous.github.io/ComfyUI_examples/video/

[User202207]

Issue persists for me aswell with amd cpu and amd 7900xtx.

Using --cpu instead of --directmL generates a video in a few minutea, but directmL spits out all that junk and asks for a four dimensional input.

I can live with it though. Just have to try to run two different installations of comfy so i dont have to keep starting and stopping the same instance to change flags.

Love ComfyUI. Thanks for giving us freedom and pure awesomeness.

[Polak149]

Is there any workaround? I too have this problem but it seems not to be very popular. I would love to generate videos using ComfyUI but using CPU is unacceptable :(

[wShuher]

same here. i would appreciate if someone could share a solution