search

TinyTerra / ComfyUI_tinyterraNodes

A selection of nodes for Stable Diffusion ComfyUI
GNU General Public License v3.0
332 stars 39 forks source link

xyPlot node sample parameters "steps" causing TypeError #81

Closed MercuryOoO closed 1 month ago

MercuryOoO commented 5 months ago

xyPlot sampler steps set to "1;7;10", I have try one line or multiple lines.

ERROR:root:Traceback (most recent call last): File "C:\Tools\AI\Data\Packages\ComfyUI\execution.py", line 155, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "C:\Tools\AI\Data\Packages\ComfyUI\execution.py", line 85, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "C:\Tools\AI\Data\Packages\ComfyUI\execution.py", line 78, in map_node_over_list results.append(getattr(obj, func)(*slice_dict(input_data_all, i))) File "C:\Tools\AI\Data\Packages\ComfyUI\custom_nodes\ComfyUI_tinyterraNodes\tinyterraNodes.py", line 1528, in sample return ttN_TSC_pipeKSampler.sample(self, pipe, lora_name, lora_model_strength, lora_clip_strength, sampler_state, steps, cfg, sampler_name, scheduler, image_output, save_prefix, denoise, File "C:\Tools\AI\Data\Packages\ComfyUI\custom_nodes\ComfyUI_tinyterraNodes\tinyterraNodes.py", line 1452, in sample return process_xyPlot(pipe, samp_model, samp_clip, samp_samples, samp_vae, samp_seed, samp_positive, samp_negative, lora_name, lora_model_strength, lora_clip_strength, steps, cfg, sampler_name, scheduler, denoise, image_output, save_prefix, prompt, extra_pnginfo, my_unique_id, preview_latent, xyPlot) File "C:\Tools\AI\Data\Packages\ComfyUI\custom_nodes\ComfyUI_tinyterraNodes\tinyterraNodes.py", line 1405, in process_xyPlot latents_plot = sampleXYplot.get_labels_and_sample(plot_image_vars, latent_image, preview_latent, start_step, last_step, force_full_denoise, disable_noise) File "C:\Tools\AI\Data\Packages\ComfyUI\custom_nodes\ComfyUI_tinyterraNodes\tinyterraNodes.py", line 764, in get_labels_and_sample self.image_list, self.max_width, self.max_height, self.latents_plot = self.sample_plot_image(plot_image_vars, latent_image, preview_latent, self.latents_plot, self.image_list, disable_noise, start_step, last_step, force_full_denoise) File "C:\Tools\AI\Data\Packages\ComfyUI\custom_nodes\ComfyUI_tinyterraNodes\tinyterraNodes.py", line 700, in sample_plot_image samples = sampler.common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, samples, denoise=denoise, disable_noise=disable_noise, preview_latent=preview_latent, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise) File "C:\Tools\AI\Data\Packages\ComfyUI\custom_nodes\ComfyUI_tinyterraNodes\tinyterraNodes.py", line 402, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, File "C:\Tools\AI\Data\Packages\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:\Tools\AI\Data\Packages\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 "C:\Tools\AI\Data\Packages\ComfyUI\comfy\samplers.py", line 669, in init self.set_steps(steps, denoise) File "C:\Tools\AI\Data\Packages\ComfyUI\comfy\samplers.py", line 690, in set_steps self.sigmas = self.calculate_sigmas(steps).to(self.device) File "C:\Tools\AI\Data\Packages\ComfyUI\comfy\samplers.py", line 681, in calculate_sigmas sigmas = calculate_sigmas_scheduler(self.model, self.scheduler, steps) File "C:\Tools\AI\Data\Packages\ComfyUI\comfy\samplers.py", line 640, in calculate_sigmas_scheduler sigmas = normal_scheduler(model, steps, sgm=True) File "C:\Tools\AI\Data\Packages\ComfyUI\comfy\samplers.py", line 317, in normal_scheduler timesteps = torch.linspace(start, end, steps + 1)[:-1] TypeError: can only concatenate str (not "int") to str

Prompt executed in 0.05 seconds

TinyTerra commented 2 months ago

V2 has added advanced xyPlot for pipeLoader_v2 and pipeLoaderSDXL_v2. There is some more detail about how it works in the readme. The old xyplot has now been deprecated