Oddities at work SDXL Refining & Noise Control Script

[BenderBlender]

with fixed all seeds it is clear that the refining seed is not fixed. which it is impossible to repeat the same image 2 times

Bug

Error occurred when executing KSampler SDXL (Eff.):

'SDXL' object has no attribute 'num_timesteps'

File "Q:_ComfyUI_windows_portable_3\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\custom_nodes\ComfyUI-0246\utils.py", line 373, in new_func res_value = old_func(final_args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 2215, in sample_sdxl return super().sample(sdxl_tuple, noise_seed, steps, cfg, sampler_name, scheduler, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 700, in sample samples, images, gifs, preview = process_latent_image(model, seed, steps, cfg, sampler_name, scheduler, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 548, in process_latent_image samples = KSamplerAdvanced().sample(model, add_noise, seed, steps, cfg, sampler_name, scheduler, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\nodes.py", line 1409, in sample return common_ksampler(model, noise_seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise, disable_noise=disable_noise, start_step=start_at_step, last_step=end_at_step, force_full_denoise=force_full_denoise) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\nodes.py", line 1345, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\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 "Q:_ComfyUI_windows_portable_3\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 241, in motion_sample return orig_comfy_sample(model, noise, args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\comfy\sample.py", line 98, in sample sampler = comfy.samplers.KSampler(real_model, steps=steps, device=model.load_device, sampler=sampler_name, scheduler=scheduler, denoise=denoise, model_options=model.model_options) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\custom_nodes\efficiency-nodes-comfyui\py\smZ_cfg_denoiser.py", line 321, in init set_model_k(self) File "Q:_ComfyUI_windows_portable_3\ComfyUI\custom_nodes\efficiency-nodes-comfyui\py\smZ_cfg_denoiser.py", line 308, in set_model_k self.model_denoise = CFGNoisePredictor(self.model) # main change ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\ComfyUI\custom_nodes\efficiency-nodes-comfyui\py\smZ_cfg_denoiser.py", line 256, in init self.inner_model2.num_timesteps = model.num_timesteps ^^^^^^^^^^^^^^^^^^^ File "Q:_ComfyUI_windows_portable_3\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1695, in getattr raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")

[jags111]

hai will look into this and update

[jags111]

hai checked your same workflow with no refiner but same

[jags111]

On the CFG noise issue the script is going thru some change and will update