Closed JasonJobsLi closed 3 weeks ago
Probably the Lora-Problem: https://github.com/comfyanonymous/ComfyUI/issues/4500
Try disabling this custom node for now: ComfyUI-Advanced-ControlNet
Try disabling this custom node for now: ComfyUI-Advanced-ControlNet现在尝试禁用此自定义节点:ComfyUI-Advanced-ControlNet
I tried it, but it doesn't work. If the updated version is returned to the 19th, it will be normal.
I got this error when matching both the 'kwaikolorswrapper' node and the 'ipadapter_plus' node
Error occurred when executing KSampler (Efficient):
ModelPatcher.calculate_weight() got an unexpected keyword argument 'intermediate_dtype'
File "D:\ComfyUI-aki-v1.3\execution.py", line 316, 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:\ComfyUI-aki-v1.3\execution.py", line 191, 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:\ComfyUI-aki-v1.3\execution.py", line 168, in _map_node_over_list process_inputs(input_dict, i) File "D:\ComfyUI-aki-v1.3\execution.py", line 157, in process_inputs results.append(getattr(obj, func)(inputs)) File "D:\ComfyUI-aki-v1.3\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 732, in sample samples, images, gifs, preview = process_latent_image(model, seed, steps, cfg, sampler_name, scheduler, File "D:\ComfyUI-aki-v1.3\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 550, in process_latent_image samples = KSampler().sample(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, File "D:\ComfyUI-aki-v1.3\nodes.py", line 1429, in sample return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise) File "D:\ComfyUI-aki-v1.3\nodes.py", line 1396, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, File "D:\ComfyUI-aki-v1.3\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 "D:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 420, in motion_sample return orig_comfy_sample(model, noise, args, kwargs) File "D:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\sampling.py", line 116, in acn_sample return orig_comfy_sample(model, *args, kwargs) File "D:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\utils.py", line 116, in uncond_multiplier_check_cn_sample return orig_comfy_sample(model, args, kwargs) File "D:\ComfyUI-aki-v1.3\comfy\sample.py", line 43, in sample samples = sampler.sample(noise, positive, negative, 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 "D:\ComfyUI-aki-v1.3\comfy\samplers.py", line 829, 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 "D:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-BrushNet\model_patch.py", line 120, in modified_sample return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) File "D:\ComfyUI-aki-v1.3\comfy\samplers.py", line 716, in sample output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) File "D:\ComfyUI-aki-v1.3\comfy\samplers.py", line 695, in inner_sample samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) File "D:\ComfyUI-aki-v1.3\comfy\samplers.py", line 600, 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:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(args, kwargs) File "D:\ComfyUI-aki-v1.3\comfy\k_diffusion\sampling.py", line 1068, in sample_euler_cfg_pp denoised = model(x, sigma_hat * s_in, extra_args) File "D:\ComfyUI-aki-v1.3\comfy\samplers.py", line 299, in call out = self.inner_model(x, sigma, model_options=model_options, seed=seed) File "D:\ComfyUI-aki-v1.3\comfy\samplers.py", line 682, in call return self.predict_noise(args, kwargs) File "D:\ComfyUI-aki-v1.3\comfy\samplers.py", line 685, 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:\ComfyUI-aki-v1.3\comfy\samplers.py", line 279, in sampling_function out = calc_cond_batch(model, conds, x, timestep, model_options) File "D:\ComfyUI-aki-v1.3\comfy\samplers.py", line 228, in calc_cond_batch output = model.apply_model(inputx, timestep, c).chunk(batch_chunks) File "D:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\utils.py", line 68, in apply_model_uncond_cleanup_wrapper return orig_apply_model(self, args, kwargs) File "D:\ComfyUI-aki-v1.3\comfy\model_base.py", line 142, in apply_model model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, extra_conds).float() File "D:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "D:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(args, kwargs) File "D:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Kolors-MZ\hook_comfyui_kolors_v2.py", line 71, in forward result = super().forward(*args, kwargs) File "D:\ComfyUI-aki-v1.3\custom_nodes\FreeU_Advanced\nodes.py", line 190, in tempforward h = forward_timestep_embed(self.middle_block, h, emb, context, transformer_options, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator) File "D:\ComfyUI-aki-v1.3\comfy\ldm\modules\diffusionmodules\openaimodel.py", line 44, in forward_timestep_embed x = layer(x, context, transformer_options) File "D:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "D:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(args, kwargs) File "D:\ComfyUI-aki-v1.3\comfy\ldm\modules\attention.py", line 694, in forward x = block(x, context=context[i], transformer_options=transformer_options) File "D:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "D:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, *kwargs) File "D:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-layerdiffuse\lib_layerdiffusion\attention_sharing.py", line 253, in forward return func(self, x, context, transformer_options) File "D:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Easy-Use\py\layer_diffuse\attension_sharing.py", line 253, in forward return func(self, x, context, transformer_options) File "D:\ComfyUI-aki-v1.3\comfy\ldm\modules\attention.py", line 621, in forward n = self.attn2(n, context=context_attn2, value=value_attn2) File "D:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(args, kwargs) File "D:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, kwargs) File "D:\ComfyUI-aki-v1.3\comfy\ldm\modules\attention.py", line 467, in forward k = self.to_k(context) File "D:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "D:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(args, kwargs) File "D:\ComfyUI-aki-v1.3\comfy\ops.py", line 67, in forward return self.forward_comfy_cast_weights(*args, **kwargs) File "D:\ComfyUI-aki-v1.3\comfy\ops.py", line 62, in forward_comfy_cast_weights weight, bias = cast_bias_weight(self, input) File "D:\ComfyUI-aki-v1.3\comfy\ops.py", line 48, in cast_bias_weight weight = s.weight_function(weight) File "D:\ComfyUI-aki-v1.3\comfy\model_patcher.py", line 99, in call return self.model_patcher.calculate_weight(self.model_patcher.patches[self.key], weight, self.key, intermediate_dtype=weight.dtype)
Can confirm that there is a problem with the latest comfyui version when using a flux lora. I'm getting the same error:
Error occurred when executing SamplerCustomAdvanced:
ModelPatcher.calculate_weight() got an unexpected keyword argument 'intermediate_dtype'
File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/execution.py", line 316, 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 "/home/marvin/AI_Image/ComfyUIs/ComfyUI/execution.py", line 191, 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 "/home/marvin/AI_Image/ComfyUIs/ComfyUI/execution.py", line 168, in _map_node_over_list process_inputs(input_dict, i) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/execution.py", line 157, in process_inputs results.append(getattr(obj, func)(inputs)) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy_extras/nodes_custom_sampler.py", line 612, 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 "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/samplers.py", line 716, in sample output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/samplers.py", line 695, in inner_sample samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/samplers.py", line 600, in sample samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, self.extra_options) File "/home/marvin/miniconda3/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, kwargs) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/k_diffusion/sampling.py", line 144, in sample_euler denoised = model(x, sigma_hat * s_in, *extra_args) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/samplers.py", line 299, in call out = self.inner_model(x, sigma, model_options=model_options, seed=seed) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/samplers.py", line 682, in call return self.predict_noise(args, kwargs) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/samplers.py", line 685, 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 "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/samplers.py", line 279, in sampling_function out = calc_cond_batch(model, conds, x, timestep, model_options) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/custom_nodes/ComfyUI-TiledDiffusion/.patches.py", line 4, in calc_cond_batch return calc_cond_batch_original_tiled_diffusion_694dbdeb(model, conds, x_in, timestep, model_options) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/samplers.py", line 228, in calc_cond_batch output = model.apply_model(inputx, timestep, c).chunk(batch_chunks) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/custom_nodes/ComfyUI-Advanced-ControlNet/adv_control/utils.py", line 68, in apply_model_uncond_cleanup_wrapper return orig_apply_model(self, args, kwargs) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/model_base.py", line 142, in apply_model model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, extra_conds).float() File "/home/marvin/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl return self._call_impl(args, kwargs) File "/home/marvin/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl return forward_call(*args, kwargs) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/ldm/flux/model.py", line 159, in forward out = self.forward_orig(img, img_ids, context, txt_ids, timestep, y, guidance, control) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/ldm/flux/model.py", line 130, in forward_orig img = block(img, vec=vec, pe=pe) File "/home/marvin/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "/home/marvin/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl return forward_call(args, kwargs) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/ldm/flux/layers.py", line 225, in forward qkv, mlp = torch.split(self.linear1(x_mod), [3 self.hidden_size, self.mlp_hidden_dim], dim=-1) File "/home/marvin/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl return self._call_impl(args, kwargs) File "/home/marvin/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl return forward_call(*args, *kwargs) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/ops.py", line 67, in forward return self.forward_comfy_cast_weights(args, kwargs) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/ops.py", line 62, in forward_comfy_cast_weights weight, bias = cast_bias_weight(self, input) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/ops.py", line 48, in cast_bias_weight weight = s.weight_function(weight) File "/home/marvin/AI_Image/ComfyUIs/ComfyUI/comfy/model_patcher.py", line 99, in call return self.model_patcher.calculate_weight(self.model_patcher.patches[self.key], weight, self.key, intermediate_dtype=weight.dtype)
can confirm that at least commit 39f114c44bb99d4a221e8da451d4f2a20119c674 is working
can confirm that at least commit 39f114c is working
yeah, version 20th and above will encounter this issue (with lora), now I'm at the 19th version and everything is fine
Odd. I'm having this problem on one machine, but not on the other - both updated to latest..
SD15 lora works well but sdxl failed, latest update. Back to 19th commit everything is ok.
i have the same situation ,some times when i restart the comfyui it works,when i change different image then come out this error...i updated my comfyui today....
I deleted my venv, rebuilt it and reinstalled all dependencies, and is working again. previously was using torch 2.3.0, is now on torch 2.4.0
I have the same problem. I get this error message after a few generations.
Should I wait for an update or revert? How to revert without having to reinstall everything?
I have the same problem. I get this error message after a few generations.
Should I wait for an update or revert? How to revert without having to reinstall everything?
Downgrade numpy==1.26.4
.
As many side effects have been occurring due to numpy
being updated to the latest version(2.0), recent measures have been taken to ensure that numpy<2 is
installed when setting up dependencies.
I deleted my venv, rebuilt it and reinstalled all dependencies, and is working again. previously was using torch 2.3.0, is now on torch 2.4.0
Thanks, I did it with this method!
run this code in cmd:
pip install torch==2.4.0+cu121 torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
Expected Behavior
The sampling process should complete without errors.
Actual Behavior
just fail to complete the drawing.
Steps to Reproduce
when I use any workflow besides official FLUX.1 workflow (e.g. https://civitai.com/models/618578/flux-dev-hi-res-fix-img2img-in-and-out-paint-wildcards-loras-ultimate-sd-upscaler-controlnet?modelVersionId=703980), will occur this problem.
Debug Logs
Other
No response