Update broke PuLID

[Pantonia4]

Expected Behavior

It should just work and run i guess

Actual Behavior

Gives an Error and doesnt work.

Steps to Reproduce

Just use PuLID.

Debug Logs

!!! Exception during processing !!! forward_orig() takes from 7 to 9 positional arguments but 10 were given
Traceback (most recent call last):
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\execution.py", line 323, in execute
    output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\execution.py", line 198, in get_output_data
    return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy_extras\nodes_custom_sampler.py", line 633, in sample
    samples = guider.sample(noise.generate_noise(latent), latent_image, sampler, sigmas, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=noise.seed)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\samplers.py", line 740, in sample
    output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\samplers.py", line 719, in inner_sample
    samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\samplers.py", line 624, 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:\AI\StabilityMatrix\Packages\ComfyUI\venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\k_diffusion\sampling.py", line 155, in sample_euler
    denoised = model(x, sigma_hat * s_in, **extra_args)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\samplers.py", line 299, in __call__
    out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\samplers.py", line 706, in __call__
    return self.predict_noise(*args, **kwargs)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\samplers.py", line 709, 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 "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\samplers.py", line 279, in sampling_function
    out = calc_cond_batch(model, conds, x, timestep, model_options)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\samplers.py", line 228, in calc_cond_batch
    output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\model_base.py", line 144, in apply_model
    model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "D:\AI\StabilityMatrix\Packages\ComfyUI\comfy\ldm\flux\model.py", line 181, in forward
    out = self.forward_orig(img, img_ids, context, txt_ids, timestep, y, guidance, control, transformer_options)
TypeError: forward_orig() takes from 7 to 9 positional arguments but 10 were given

Other

Going back one version makes it work again.

[amao2001]

the same error
forward_orig() takes from 7 to 9 positional arguments but 10 were given

[ltdrdata]

This is a backward compatibility issue.
This should be handled in the PuLID custom node repo.
Please move this issue to the repo.

[adydeejay]

It seems that the problem comes from this line. I modified it back to this and now image generation works with PuLID.

Please note that this is a temporary workaround for simple workflows with PuLID and is not a permanent fix; it may also impact the functionality of other nodes.

[Madushan996]

It seems that the problem comes from this line. I modified it back to this and now image generation works with PuLID.

Thank you

[Malie73]

It seems that the problem comes from this line. I modified it back to this and now image generation works with PuLID.

Great, thank you!

[fogostudio]

It seems that the problem comes from this line. I modified it back to this and now image generation works with PuLID.

Please note that this is a temporary workaround for simple workflows with PuLID and is not a permanent fix; it may also impact the functionality of other nodes.

That worked, thanks!

[prog-ape]

After updating to the latest version, several plugins have this problem.
ComfyUI-Advanced-ControlNet This plug-in will also affect

[ialhabbal]

It seems that the problem comes from this line. I modified it back to this and now image generation works with PuLID.
Please note that this is a temporary workaround for simple workflows with PuLID and is not a permanent fix; it may also impact the functionality of other nodes.

That worked, thanks!

The file was updated with your fix with the latest update, but still I get the same error.

File "L:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\comfy\ldm\flux\model.py", line 181, in forward
out = self.forward_orig(img, img_ids, context, txt_ids, timestep, y, guidance, control, transformer_options)

I removed the transformer_options from the line, and it solved the problem. But the generation seems pretty slow.

[songkangfeng]

update to the latest version ,it doesn't work

[chenpipi0807]

不管事啊老师

[2129518511]

删除transformer_options使pulid完全失效了

以上问题是影响了大模型导致，更换大模型可以解决

[Fipu-merged]

For some reason code change in model.py resultet in Boolean value of Tensor with more than one value is ambiguous

[stoutimon]

It seems that the problem comes from this line. I modified it back to this and now image generation works with PuLID.

Please note that this is a temporary workaround for simple workflows with PuLID and is not a permanent fix; it may also impact the functionality of other nodes.

this has worked for me too

[sorc1900]

Does this fix work with portable?

[trai78]

Go into your comfyui folder > cmd > git reset --hard cc9cf6d1bd957d764ad418258b61d7e08187573b

[yropbv]

It seems that the problem comes from this line. I modified it back to this and now image generation works with PuLID.

Please note that this is a temporary workaround for simple workflows with PuLID and is not a permanent fix; it may also impact the functionality of other nodes.

SamplerCustomAdvanced
Boolean value of Tensor with more than one value is ambiguous

I get this after changing this

[adydeejay]

sipie800/ComfyUI-PuLID-Flux-Enhanced#27

[aprisma2008]

Go into your comfyui folder > cmd > git reset --hard cc9cf6d1bd957d764ad418258b61d7e08187573b

This works of course because it sets back to an older version. But then all the good new things like LTX Video aso. do not work any more. So till this is solved we have to switch between the version case to case. I hope they fix it with the new desktop model :-)

[swdvb]

Go into your comfyui folder > cmd > git reset --hard cc9cf6d

Then start your comfy, it should help.

[chenpipi0807]

git reset --hard a72d152

看起来我回退到了远古版本

[CaptailTyler]

The issue has now been fixed. Just update your FLUX PULID vis ComfyUI Manager.

Edit: Was still getting "Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!"

Please follow the fix from adydeejay below, as it has solved all issues for me now. No more speed issues too.

[cgl13207205048]

此问题现已修复。只需使用 ComfyUI Manager 更新您的 FLUX PULID 即可。

编辑：仍然收到“预期所有张量都在同一设备上，但发​​现至少两个设备，cuda：0 和 cpu！”

请按照下面 adydeejay 的修复方法操作，因为它现在已经为我解决了所有问题。也不再有速度问题。

我试过更新comfyui和flux_pulid都不行

[nzmajid77]

I got the same problem. But today after I have updated my ComfyUI, the error is gone.

[chenpipi0807]

forward_orig() takes from 7 to 9 positional arguments but 10 were given
这个问题依然存在
pulid插件也是最新版

[faizzed]

Use this repo instead https://github.com/zhangp365/ComfyUI-PuLID-Flux