hey, very nice workflow, where i find controlnet models from your workflow i have different ones and one from 1.5 can you please give me the link, i  m little confused with controlnet sdxl models, sometimes are 200 mb big sometimes are like odl 1.5 a1111 2 or 3 gb?

weibo上旋转的女孩工作流能提供吗博主

hey i manage to find controlnets, but i get this message and am fine with ipadapter i have updatet it

Error occurred when executing IPAdapterUnifiedLoader: IPAdapter model not found. File "C:\Users\User\Desktop\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\User\Desktop\ComfyUI\ComfyUI_windows_portable\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 "C:\Users\User\Desktop\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\User\Desktop\ComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 454, in load_models raise Exception("IPAdapter model not found.")

Wowwww! You're awesome! This is so super cool, I tried it out and I'm really really loving the results )))

where is "ttplanetSDXLControlnet_v10Fp16_tile.safetensors" ?

Why my workflow stop at here:

[AnimateDiffEvo] - INFO - Sliding context window activated - latents passed in (374) greater than context_length 8.

[AnimateDiffEvo] - INFO - Using motion module mm_sdxl_v10_beta.ckpt:v1.

Requested to load ControlNet

Requested to load ControlNet

Requested to load AnimateDiffModel

Requested to load ControlNet

Requested to load SDXL

Loading 5 new models

0%|                                                                                            | 0/8 [00:00<?, ?it/s]

Error occurred when executing IPAdapterUnifiedLoader: IPAdapter model not found. File "G:\Ai\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\Ai\ComfyUI_windows_portable\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 "G:\Ai\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\Ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 454, in load_models raise Exception("IPAdapter model not found.")

ComfyUI\models\clip_vision

On this path
CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors
CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors

I still get an error message. Even if I update it, it's still a problem.

where is diffusers_xl_depth_full.safetensors

Thank you so much for your kindness and support.

Error occurred when executing ColorMatch: Can't import color-matcher, did you install requirements.txt? Manual install: pip install color-matcher

这个如何去解决

KSampler: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! File "G:\Ai\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\Ai\ComfyUI_windows_portable\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 "G:\Ai\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\Ai\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1344, in sample return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\Ai\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1314, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\Ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 22, in informative_sample raise e File "G:\Ai\ComfyUI_windows_portable\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 "G:\Ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 383, in motion_sample latents = orig_comfy_sample(model, noise, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\Ai\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\control_reference.py", line 47, in refcn_sample return orig_comfy_sample(model, *args, **kwargs)

Can't I get 8GB of VRAM???

执行 ADE_AnimateDiffLoaderGen1 时出错：cumprod() 收到无效的参数组合 - 得到（numpy.ndarray，dim=int），但预期以下之一：*（Tensor input，int dim，*，torch.dtype dtype，Tensor out）*（Tensor input，name dim，*，torch.dtype dtype，Tensor out）文件“D:\AI\ConfyUI-aki\ComfyUI-aki-v1.3\execution.py”，第 151 行，在 recursive_execute output_data 中，output_ui = get_output_data（obj，input_data_all）文件“D:\AI\ConfyUI-aki\ComfyUI-aki-v1.3\execution.py”，第 81 行，在 get_output_data return_values = map_node_over_list（obj，input_data_all，obj.FUNCTION，allow_interrupt=True）文件“D:\AI\ConfyUI-aki\ComfyUI-aki-v1.3\execution.py”, 第 74 行, 在 map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) 文件“D:\AI\ConfyUI-aki\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\nodes_gen1.py”, 第 95 行, 在 load_mm_and_inject_params new_model_sampling = BetaSchedules.to_model_sampling(beta_schedule, model) 文件“D:\AI\ConfyUI-aki\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\utils_model.py”, 第 167 行, 在 to_model_sampling return cls._to_model_sampling（别名=别名，model_type=model.model.model_type）文件“D:\AI\ConfyUI-aki\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\utils_model.py”，第 162 行，在 _to_model_sampling 中 ms_obj = evolve_model_sampling（cls.to_config（别名），model_type=model_type，别名=别名，original_timesteps=original_timesteps）文件“D:\AI\ConfyUI-aki\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\utils_model.py”，第 79 行，在 evolve_model_sampling 中返回 model_sampling（model_config，model_type）文件“D:\AI\ConfyUI-aki\ComfyUI-aki-v1.3\comfy\model_base.py”，第 45 行，在 model_sampling 中返回 ModelSampling(model_config) 文件“D:\AI\ConfyUI-aki\ComfyUI-aki-v1.3\comfy\model_sampling.py”，第 50 行，在 __init__ 中 self._register_schedule(given_betas=None, beta_schedule=beta_schedule, timesteps=1000, linear_start=linear_start, linear_end=linear_end, cosine_s=8e-3) 文件“D:\AI\ConfyUI-aki\ComfyUI-aki-v1.3\comfy\model_sampling.py”，第 60 行，在 _register_schedule 中 alphas_cumprod = torch.cumprod(alphas, dim=0)

执行 ADE_AnimateDiffLoaderGen1 时出错：join() 参数必须是 str、bytes 或 os.PathLike 对象，而不是 'NoneType' 文件“D:\AIGC-666\ConfyUI-aki\ComfyUI-aki-v1.3\execution.py”，第 151 行，在 recursive_execute output_data 中，output_ui = get_output_data(obj, input_data_all) 文件“D:\AIGC-666\ConfyUI-aki\ComfyUI-aki-v1.3\execution.py”，第 81 行，在 get_output_data 中 return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) 文件“D:\AIGC-666\ConfyUI-aki\ComfyUI-aki-v1.3\execution.py”，第 74 行，在 map_node_over_list 中results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) 文件“D:\AIGC-666\ConfyUI-aki\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\nodes_gen1.py”，第 50 行，在 load_mm_and_inject_params motion_model = load_motion_module_gen2(model_name=model_name, motion_model_settings=ad_settings) 文件“D:\AIGC-666\ConfyUI-aki\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\model_injection.py”，第 1229 行，在 load_motion_module_gen2 model_path = get_motion_model_path(model_name) 文件“D:\AIGC-666\ConfyUI-aki\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\utils_model.py”，第 346 行，在 get_motion_model_path 中返回 folder_paths.get_full_path(Folders.ANIMATEDIFF_MODELS, model_name) 文件“D:\AIGC-666\ConfyUI-aki\ComfyUI-aki-v1.3\folder_paths.py”，第 179 行，在 get_full_path 中 filename = os.path.relpath(os.path.join("/", filename), "/") 文件“D:\AIGC-666\ConfyUI-aki\ComfyUI-aki-v1.3\python\lib\ntpath.py”，第 143 行，在 join genericpath._check_arg_types('join', path, *paths)文件“D:\AIGC-666\ConfyUI-aki\ComfyUI-aki-v1.3\python\lib\genericpath.py”，第 152 行，在 _check_arg_types 中引发 TypeError(f'{funcname}() 参数必须是 str、bytes 或 '

comfyui萌新请教

解决了七八个errors之后终于跑通了workflow，但结果不太理想，最终效果看上去噪点很高，请问有人知道要怎么调整吗？

相比楼主原来的workflow，改了第二个controlNet的aio preprocessor为depthAnything（原为zoe depthAnything）；

将cfg从2.0改为了1.0；

采样器保持dpmpp_sde；

scheduler保持karras

试了一整天了，不管怎么调参都无法达到楼主这样的效果。我现在怀疑是不是我用的controlNet模型有问题。楼主3个controlNet中的后两个分别使用diffusers_xl_depth_full.safetensors 和 diffusers_xl_canny_full.safetensors，我都是用diffusion_pytorch_model.safetensors（因为搜索这两个controlNet实在找不到，在huggingface的diffusers下找到了我使用的这个，拿来代替了）

还有第二个controlNet楼主AIO使用Zoe_DepthAnythingPreprocessor, 我使用DepthAnythingV2Preprocessor，因为前者直接报错（似乎还是找不到这个preprocessor，但理论上应该自动下载，不知道这个为什么没有）。

求教有人知道问题出在哪吗，我可以提供workflow和素材，或者有好心人能给我👆提到的2个controlNet吗

Though I managed to run the workflow, when it reaches the ksampler it gets stuck and won't progress further. it says it's on 85% and it freezes after "loading 5 models". any ideas on how to tackle this?

Where does the PLUS (high strength) model for IPAdapter  Unified Loader came from??? I have being looking for it the entire afternoon....

这个叫 PLUS (high strength) 的模块在哪下啊。。找了一整天了都找不到。。。

Discord  在线运行，已经替换了视频上传，怎么还是报错呢？

Error occurred when executing VAELoader: 'NoneType' object has no attribute 'lower' File "/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/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 "/ComfyUI/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/ComfyUI/nodes.py", line 689, in load_vae sd = comfy.utils.load_torch_file(vae_path) File "/ComfyUI/comfy/utils.py", line 13, in load_torch_file if ckpt.lower().endswith(".safetensors"):

🚀 Now you can Edit & Run it online (Fast & Error Free):

该工作流在线编辑运行地址：（速度快，不爆红）

https://www.runninghub.ai/post/1866056401050357762/?utm_source=openart

https://www.runninghub.cn/post/1866016887959142402/?utm_source=openart

RunningHub – Highly reliable Cloud-Based ComfyUI, Edit and Run Workflows Online, no local installation required. Powered by RTX 4090 GPUs for faster performance and fully error-free node operation.

RunningHub - 超高可用性云端ComfyUI，本地免安装，标配RTX4090带来更快运行速度，站内已发布海量高质量工作流可一键运行，速度快，不爆红

-------------------------------------

👋🏻 Hello Simon Lee,    
I’m Spike from RunningHub.  I hope this message finds you well! I wanted to kindly inform you that we’ve copied your workflow to RunningHub (with the original author clearly credited and a link to your OpenArt profile). The purpose is to allow more users who love your work to easily experience it online.  
We’d love to hear from you at: spike@runninghub.ai
🎉 If you’re open to joining us, we can transfer the workflows we’ve uploaded to your RunningHub account and provide you with additional benefits as a token of our appreciation.
😞 However, if you’re not comfortable with this approach, we will promptly remove all the uploaded content.    
Looking forward to your response!

Hey! I love this flow! Great work and thanks for sharing. How did you achieve such a noise free result? I get it all working but it feels noisey. Not that clean as your examples.