CLIP Text Encode (Advanced) errors as of new ComfyUI commit

[bazettfraga]

Hi, as of ComfyUI commit https://github.com/comfyanonymous/ComfyUI/commit/e60ca6929a999f53a4eeb62cc80f70b1cd7a0acf the node seems to throw out the following error down below, refusing to begin generating at all. Reverting to https://github.com/comfyanonymous/ComfyUI/commit/6ec3f12c6e2e1d214c41f5713308818541da52a4 fixes this issue, leading me to believe that the changes in the tokenizer are responsible for this issue:

ERROR:root:Traceback (most recent call last):
  File "/mnt/2TBDa/SDSoftware/ComfyUI/execution.py", line 153, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/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 "/mnt/2TBDa/SDSoftware/ComfyUI/execution.py", line 76, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/nodes.py", line 1237, in sample
    return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/nodes.py", line 1207, in common_ksampler
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/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/2TBDa/SDSoftware/ComfyUI/comfy/samplers.py", line 728, 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/2TBDa/SDSoftware/ComfyUI/comfy/samplers.py", line 633, in sample
    samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/comfy/samplers.py", line 589, in sample
    samples = getattr(k_diffusion_sampling, "sample_{}".format(sampler_name))(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **extra_options)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/salt/.local/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/comfy/k_diffusion/sampling.py", line 580, in sample_dpmpp_2m
    denoised = model(x, sigmas[i] * s_in, **extra_args)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/salt/.local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/salt/.local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/comfy/samplers.py", line 287, in forward
    out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/salt/.local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/salt/.local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/comfy/k_diffusion/external.py", line 129, in forward
    eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/comfy/k_diffusion/external.py", line 155, in get_eps
    return self.inner_model.apply_model(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/comfy/samplers.py", line 275, in apply_model
    out = sampling_function(self.inner_model.apply_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/comfy/samplers.py", line 253, in sampling_function
    cond, uncond = calc_cond_uncond_batch(model_function, cond, uncond, x, timestep, max_total_area, model_options)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/comfy/samplers.py", line 229, in calc_cond_uncond_batch
    output = model_function(input_x, timestep_, **c).chunk(batch_chunks)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/2TBDa/SDSoftware/ComfyUI/comfy/model_base.py", line 62, in apply_model
    context = context.to(dtype)
              ^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'to'

Thank you for your help in advance!

[HaydenReeve]

I'm finding a similar issue with the regular KSampler too.

Error occurred when executing KSampler:

'NoneType' object has no attribute 'to'

File "E:\AI\ComfyUI\execution.py", line 153, in recursive_execute

Reverted back to the native Text Encoder (New) and the workflow runs without issue.

[925-Studio]

Same problem here. I'm using Efficiency custom nodes, I set positive and negative input from text and they work fine til the last update of ComfyUI.

Error occurred when executing KSampler (Efficient):

'NoneType' object has no attribute 'cpu'

File "/root/sd-comfyui/execution.py", line 153, in recursive_execute

Switch to regular text encode works no problem.

[Martillo9]

Same problems... first, I got some color noise corrupt images, then KSampler stop working and gave me those errors... Please help, somebody save us!

[BlenderNeko]

should be fixed now

[liulsg]

should be fixed now

@BlenderNeko
I just tested it, and it's still wrong.

[BlenderNeko]

@liulsg I can't really do anything with that. Are these my nodes or someone else's? what are the current commit short hashes of both ComfyUI and ComfyUI_ADV_CLIP_emb? (you can check this by running git rev-parse --short HEAD in the respective folders), what is the error message that it throws?

[0xmihutao]

works for me now

[Martillo9]

Yeah, I updated it by running those 2 bat files in the update folder. And now I was able to make a simple image, the Ksampler didn´t crash...

[momognu]

list indices must be integers or slices, not str

[jhlchu]

Latest ComfyUI gives this error:

Error occurred when executing BNK_CLIPTextEncodeAdvanced:

The expanded size of the tensor (308) must match the existing size (154) at non-singleton dimension 1. Target sizes: [1, 308, 768]. Tensor sizes: [1, 154, 1]

for comfy++ and A1111 option.

[momognu]

update comfyui, be kill 99% of problems

[lizhuting9229]

I'm finding a similar issue with the regular KSampler too.

Error occurred when executing KSampler:

'NoneType' object has no attribute 'to'

File "E:\AI\ComfyUI\execution.py", line 153, in recursive_execute

Reverted back to the native Text Encoder (New) and the workflow runs without issue.

Hi, have you solved it? I met the same problem.

[cinos777]

I'm finding a similar issue with the regular KSampler too.

Error occurred when executing KSampler:

'NoneType' object has no attribute 'to'

File "E:\AI\ComfyUI\execution.py", line 153, in recursive_execute

Reverted back to the native Text Encoder (New) and the workflow runs without issue.

Hello! Please tell me how to switch to this encoder in ComfyUI