KeyError: 'sigmas' when on KSampler with SD1.5

[Gerkinfeltser]

When running the attached (or more elaborate) SD1.5 workflow using the Layer Diffuse Apply node, the KSampler stage errors out with the following output. When swapping models & relevant fields to SDXL this error does not occur.

Please let me know what you can advise. Thank you!

!!! Exception during processing !!!
Traceback (most recent call last):
  File "C:\ai\ComfyUI\execution.py", line 151, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\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 "C:\ai\ComfyUI\custom_nodes\ComfyUI-0246\utils.py", line 381, in new_func
    res_value = old_func(*final_args, **kwargs)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\execution.py", line 74, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\nodes.py", line 1368, in sample
    return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\nodes.py", line 1338, in common_ksampler
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\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 "C:\ai\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 "C:\ai\ComfyUI\comfy\samplers.py", line 703, in sample
    return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\samplers.py", line 608, in sample
    samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\samplers.py", line 547, 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\vector\.conda\envs\comfyui\Lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\k_diffusion\sampling.py", line 137, in sample_euler
    denoised = model(x, sigma_hat * s_in, **extra_args)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\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 "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\samplers.py", line 272, in forward
    return self.apply_model(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\samplers.py", line 269, in apply_model
    out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\custom_nodes\comfyui-art-venture\modules\fooocus\patch.py", line 270, in sampling_function_patched
    cond, uncond = calc_cond_uncond_batch(model, cond, uncond, x, timestep, model_options)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\custom_nodes\comfyui-art-venture\modules\fooocus\patch.py", line 241, in calc_cond_uncond_batch
    output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\model_base.py", line 96, in apply_model
    model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\custom_nodes\comfyui-art-venture\modules\fooocus\patch.py", line 296, in unet_forward_patched
    h = forward_timestep_embed(module, h, emb, context, transformer_options)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 43, in forward_timestep_embed
    x = layer(x, context, transformer_options)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\ldm\modules\attention.py", line 632, in forward
    x = block(x, context=context[i], transformer_options=transformer_options)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\custom_nodes\ComfyUI-layerdiffusion\lib_layerdiffusion\attention_sharing.py", line 253, in forward
    return func(self, x, context, transformer_options)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\ldm\modules\attention.py", line 459, in forward
    return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\ldm\modules\diffusionmodules\util.py", line 191, in checkpoint
    return func(*inputs)
           ^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\comfy\ldm\modules\attention.py", line 519, in _forward
    n = self.attn1(n, context=context_attn1, value=value_attn1)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\vector\.conda\envs\comfyui\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ai\ComfyUI\custom_nodes\ComfyUI-layerdiffusion\lib_layerdiffusion\attention_sharing.py", line 192, in forward
    transformer_options["sigmas"],
    ~~~~~~~~~~~~~~~~~~~^^^^^^^^^^
KeyError: 'sigmas'

Prompt executed in 0.16 seconds

[huchenlei]

Please specify the ComfyUI version you are using.

[Gerkinfeltser]

ComfyUI: 2057[65397c](2024-03-10) Please let me know if you need more information.

[huchenlei]

I cannot reproduce the issue. SDXL is fine because SDXL config does not use attention sharing. You can add a print call to check whether following line get called before the error:

ComfyUI-layerdiffuse/lib_layerdiffusion/attention_sharing.py

Line 252 in 151f746

cls.transformer_options = transformer_options

[Gerkinfeltser]

The debug print appear to run once (line 233 [2024-03-11 15:15] HELLOOOOOOOOOOOOO!!!!!!!!!!!) before the error occurs. I'm attaching my most recent comfyui.log. It just has the startup & then kicking off the queue of the above workflow.

comfyCrash.log

[huchenlei]

Does the key error disappear? The new error seems to be the same as #52

[Gerkinfeltser]

Oh my! It did didn't it. That looks to be the same yes. Sorry for not looking more closely!

[huchenlei]

For the CUDA error, you can try disasble xformers according to comfyanonymous/ComfyUI#2836 (comment)

[Gerkinfeltser]

That did the trick! Thank you! Not sure what happened with my sigma error from above. Anyway, I'll close this now.

Thanks again

[Gerkinfeltser]

Hi again, actually this is still an issue I see. (The other issue threw me off.)

Getting the same old Sigma errors when running the original workflow (plus others I've tried creating from scratch). FWIW I made sure to start the workflow from a fresh server startup. I was also able to get some to work so its seems a bit unpredictable/intermitten...