facedetailer and certain controlnet model compatibility issues

[ytoaa]

!!! Exception during processing!!! '>' not supported between instances of 'NoneType' and 'float' Traceback (most recent call last): File "Q:\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "Q:\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 "Q:\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) File "Q:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 557, in doit enhanced_img, cropped_enhanced, cropped_enhanced_alpha, mask, cnet_pil_list = FaceDetailer.enhance_face( File "Q:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 513, in enhance_face DetailerForEach.do_detail(image, segs, model, clip, vae, guide_size, guide_size_for_bbox, max_size, seed, steps, cfg, File "Q:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 289, in do_detail enhanced_image, cnet_pils = core.enhance_detail(cropped_image, model, clip, vae, guide_size, guide_size_for_bbox, max_size, File "Q:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 333, in enhance_detail refined_latent = impact_sampling.ksampler_wrapper(model2, seed2, steps2, cfg2, sampler_name2, scheduler2, positive2, negative2, File "Q:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_sampling.py", line 217, in ksampler_wrapper refined_latent = separated_sample(model, True, seed, advanced_steps, cfg, sampler_name, scheduler, File "Q:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_sampling.py", line 190, in separated_sample res = sample_with_custom_noise(model, add_noise, seed, cfg, positive, negative, impact_sampler, sigmas, latent_image, noise=noise, callback=callback) File "Q:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_sampling.py", line 143, in sample_with_custom_noise samples = comfy.sample.sample_custom(model, noise, cfg, sampler, sigmas, positive, negative, latent_image, noise_mask=noise_mask, callback=touched_callback, disable_pbar=disable_pbar, seed=noise_seed) File "Q:\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\control_reference.py", line 47, in refcn_sample return orig_comfy_sample(model, *args, *kwargs) File "Q:\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\utils.py", line 112, in uncond_multiplier_check_cn_sample return orig_comfy_sample(model, args, kwargs) File "Q:\ComfyUI\comfy\sample.py", line 48, in sample_custom samples = comfy.samplers.sample(model, noise, positive, negative, cfg, model.load_device, sampler, sigmas, model_options=model.model_options, latent_image=latent_image, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed) File "Q:\ComfyUI\custom_nodes\ComfyUI_smZNodes\smZNodes.py", line 1470, in sample return _sample(args, kwargs) File "Q:\ComfyUI\comfy\samplers.py", line 703, in sample return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) File "Q:\ComfyUI\comfy\samplers.py", line 690, in sample output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) File "Q:\ComfyUI\comfy\samplers.py", line 669, in inner_sample samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) File "Q:\ComfyUI\comfy\samplers.py", line 574, in sample samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, self.extra_options) File "Q:\ComfyUI\venv\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(args, kwargs) File "Q:\ComfyUI\comfy\k_diffusion\sampling.py", line 779, in sample_lcm denoised = model(x, sigmas[i] * s_in, *extra_args) File "Q:\ComfyUI\comfy\samplers.py", line 297, in call out = self.inner_model(x, sigma, model_options=model_options, seed=seed) File "Q:\ComfyUI\custom_nodes\ComfyUI_smZNodes\smZNodes.py", line 993, in call return self.predict_noise(args, kwargs) File "Q:\ComfyUI\custom_nodes\ComfyUI_smZNodes\smZNodes.py", line 1043, in predict_noise out = super().predict_noise(args, kwargs) File "Q:\ComfyUI\comfy\samplers.py", line 659, 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 "Q:\ComfyUI\custom_nodes\ComfyUI-AutomaticCFG\nodes.py", line 52, in sampling_function_patched out = comfy.samplers.calc_cond_batch(model, conds, x, timestep, model_options) File "Q:\ComfyUI\comfy\samplers.py", line 226, in calc_cond_batch output = model.apply_model(inputx, timestep, c).chunk(batch_chunks) File "Q:\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\utils.py", line 64, in apply_model_uncond_cleanup_wrapper return orig_apply_model(self, args, kwargs) File "Q:\ComfyUI\comfy\model_base.py", line 114, in apply_model model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, extra_conds).float() File "Q:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "Q:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, *kwargs) File "Q:\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 852, 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 "Q:\ComfyUI\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 44, in forward_timestep_embed x = layer(x, context, transformer_options) File "Q:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(args, kwargs) File "Q:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, kwargs) File "Q:\ComfyUI\comfy\ldm\modules\attention.py", line 694, in forward x = block(x, context=context[i], transformer_options=transformer_options) File "Q:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "Q:\ComfyUI\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(args, kwargs) File "Q:\ComfyUI\comfy\ldm\modules\attention.py", line 560, in forward n, context_attn1, value_attn1 = p(n, context_attn1, value_attn1, extra_options) File "Q:\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\control_lllite.py", line 55, in call if self.control.t > self.control.timestep_range[0] or self.control.t < self.control.timestep_range[1]: TypeError: '>' not supported between instances of 'NoneType' and 'float'

Prompt executed in 26.83 seconds

https://civitai.com/models/136070?modelVersionId=267507

I used the above control net model The uploaded image contains EXIF.

What's interesting is that it works if you leave the wildcard contents blank.

[ltdrdata]

I cannot reproduce that issue.

Update to latest version all. And disable all other custom nodes. And try again.

[ytoaa]

I cannot reproduce that issue.

Update to latest version all. And disable all other custom nodes. And try again.

After all updates in comfyui, the above workflow is imported and executed, and the same results are displayed. Would you like to take the above png file to comfyui as it is and run it?

[ltdrdata]

I cannot reproduce that issue. Update to latest version all. And disable all other custom nodes. And try again.

After all updates in comfyui, the above workflow is imported and executed, and the same results are displayed. Would you like to take the above png file to comfyui as it is and run it?

I have already tried that. Have you minimized the custom nodes and tested it?

[ytoaa]

I cannot reproduce that issue. Update to latest version all. And disable all other custom nodes. And try again.

After all updates in comfyui, the above workflow is imported and executed, and the same results are displayed. Would you like to take the above png file to comfyui as it is and run it?

I have already tried that. Have you minimized the custom nodes and tested it?

I know the cause. An error occurs as soon as I write something in the wildcard spec space.

[ltdrdata]

I cannot reproduce that issue. Update to latest version all. And disable all other custom nodes. And try again.

After all updates in comfyui, the above workflow is imported and executed, and the same results are displayed. Would you like to take the above png file to comfyui as it is and run it?

I have already tried that. Have you minimized the custom nodes and tested it?

I know the cause. An error occurs as soon as I write something in the wildcard spec space.

confirmed

[ytoaa]

I cannot reproduce that issue. Update to latest version all. And disable all other custom nodes. And try again.

After all updates in comfyui, the above workflow is imported and executed, and the same results are displayed. Would you like to take the above png file to comfyui as it is and run it?

I have already tried that. Have you minimized the custom nodes and tested it?

I know the cause. An error occurs as soon as I write something in the wildcard spec space.

confirmed

Is this a kind of bug?

[ltdrdata]

This is patched...

When using advanced controlnet, if you apply a wildcard, the positive is replaced with the wildcard's conditioning, causing a mismatch between positive and negative, which was leading to crashes.

Although it's not recommended to apply controlnet directly to FaceDetailer.