ComfyUI Detailer/ADetailer Workflow
If you're having ANY issues with this workflow, please include the error log from your console when writing a comment here on this page. Chances are 99.98% i can help you with your issue - but i need the error log. And me not having to ask for it first will save you potentially hours. Chances are also high the solution to your problem is already documented in the FAQ here.
You can now support me on my Ko-Fi if you have too much money (✿◡‿◡)
Requirements for each version are listed below or can be found inside a Note in the Workflow itself.
Because of the many connections among the nodes, I highly recommend turning off the link visibility by clicking the "Toggle Link visibility" (Eye icon) in the bottom right of ComfyUI.
Description
I originally came from A1111 WebUI to ComfyUI and, honestly, a lot of things felt way more complicated than they needed to be. I couldn’t find workflows that were both visually pleasing and showed me all the important options without requiring a deep understanding of every little thing in ComfyUI.
Over a few months I learned the ins and outs of Comfy and built my own very barebones, simple workflow (v1) with one main goal: streamline the process and make it visually understandable. I released it here thinking it might help others who also want to make the jump from A1111 to Comfy.
Over the last year I’ve kept adding more and more features as people started using the workflow and requesting things. The workflow has grown a lot, but I’m still trying to keep the same ease-of-use that this whole journey started with. The main goal is still the same: give you a lot of powerful options in a layout that’s as clean, readable, and as user-friendly as ComfyUI will allow.
At this point I feel like I have a pretty solid understanding of how Comfy works, and I’ve even created my own custom nodes to add missing functionality so this workflow could match the ideas I had for it. I try to hide as much of the technical complexity as possible — but if you’re ever curious or confused about anything, please feel free to ask!
Thanks to all of your suggestions, the workflow now includes features like:
Single-image and batch generation
Automatic detailers for specific body parts
Upscaling
v-pred models
LoRAs
ControlNet
IPAdapter
Hires fix / refiner
Manual inpainting
Thank you to every single person who uses this workflow, donates Buzz, or shares images on this page.
I really appreciate you taking those extra steps to support and promote the project. ♥️
Requirements
v4.4 and above require ComfyUI version 0.3.51 or above and also need the frontend to be AT LEAST 1.24.3 or later.
v5.1 - Full List
v5.0 - Full List
v4.4 - Additions to v4.3 (IMG2IMG Only)
Otherwise same as v4-4.3 below
v4.2-4.3 - Additions to v4.1
Otherwise same as v4.1 (incl. v4) below
v4.1 - Additions to v4 (IMG2IMG Only)
Otherwise same as v4 below
v4 - Full List
v3 - v3.2 - Full List
v2.2 - Additions to v2
Otherwise same Custom-Nodes as v2 but you can remove Comfyui-ergouzi-Nodes
v2 - Full List
v1 - Full List
How to use
Since all of the different versions work differently, you should check the "How to use" Node inside of the Workflow itself.
I promise that once you read the explanation of the workflow itself, it'll click and it will be a simple plug and play experience.
It's the simplest I could've made it coming from someone who's only started using ComfyUI 4-5 months ago and had been exclusively an A1111WebUI user before.
When were what functionalitys added?
Starting from v3, ControlNet is included.
Starting from v4, IPAdapter is included.
Starting from v4.3, HiRes Fix and Dynamic prompts(wildcards) is included.
Starting from v4.4, Refiner is included.
Starting from v5.0, Manual Inpainting is included.
Any errors during execution?
If you're running into any errors during the execution of the workflow, please check the FAQ of my Guide first. The guide is written for the IMG2IMG Workflow but when issues arise that people run into frequently i'll add the solutions and what's hapenning to that FAQ section.
If you can't find the problem you're running into there - feel free to write me a comment on the model page so that i can help you and other people might benefit from it as well.
Feedback
I'd love to see your feedback or opinion on the workflow.
This is the first workflow I have ever created myself from scratch and I'd love to hear what you think of it.
If you want to do me a huge favor, you can post your results on this Model page.
I'll make sure to send some buzz your way!
Description
Implementation of Manual inpainting
fixed refiner/normal sampler issue when activating/deactivating img2img transfer
more lazy switches implemented so workflow only runs nodes required for final result(better performance)
changed hires fix steps calculation to use the same step count if steps below 10 (lightning/dmd2 loras for low vram)
saves lora information now from all activated loras in general lora power loader
fixed a bug that saved your exclusion tags as positive prompt when not using img2img transfer
removed Anything Anywhere nodes due to repeating problems after comfy updates since introduction of subgraphs
added a slider for the color fix strength
FAQ
Comments (47)
i have a problem with de nympy version needed for ComfyUI-WD14-Tagger, any advice? i don't want to downgrade numpy cause it could break other files
Hey @elmejor9369,
this is the first time i have someone running into this issue :O What is your error log showing?
does the workflow work for colab hosting?
@vslinx yeah the output is just saving one image, so if there isnt much that can be done to stop it then it's fine. no image was appearing on the two preview nodes, and basically the image just passes trough the workflow and comes out unchanged no matter the denoise scale, and now im having a this error suddenly:
vsLinx_LoadSelectedImagesList
Load (Multiple) Images (List): No valid images found. They may have been moved or deleted from the input folder.
im using the images on the input folder and, whatever image i try to input also arent being previewed anymore after this error happens, and just small detail because idk it could help you diagnose ig, when the preview would appear, it doesnt show the dimensions details of the picture under it.
not sure if it's because of the hosting method not being compatible, but if it is im just gonna link it since it could help you plan next versions to be cloud compatible IF that is the case: civitai.com/articles/21835/keep-generating-anything-no-yellow-buzz-no-strong-gpu-no-limits-for-free.
And sorry if im not making a lot of sense lol, im very much a amateur at this method of generation so take everything im saying with the biggest spoon of salt.
Hey @BalmoAI,
sadly i think there's not much that i can do to fix this :/
This is a problem exclusively with collab since your container get's thrown out once your time runs out and you have to set it up again.
The error you're seeing is because the file it's referencing is no longer in the input folder.
In ComfyUI the "select image" process works that way that you select images and these images upon selecting are being copied to your input folder inside comfyui.
Obviously if your image is deleted, removed or renamed the reference doesn't exist anymore. The preview might still show since the preview is loaded into the cache - but once you start the actual workflow the image isn't there so the error is being thrown.
In these cases dimensions are then also not being shown anymore since the information cannot be called on these files anymore.
It's also somewhat counter-intuitive but when you open a new colab/installation of ComfyUI, you always have to refresh the window where you have it open once by pressing F5 or clicking the refresh button.
Even across different url's and installations your browser persists all cached comfy data, so you might see a preview that's not there anymore and some nodes may not work because the shown nodes are still pointing towards your old colab/installation.
The workflow is already colab compatible and tested, the problem with colab is that you basically have to throw away the container after a few hours again once the free time runs out and then have to set it up again. Then most people don't clear the comfy cache and work on half cached versions that mismatch what's present on the hard drive of the colab :/
@vslinx sorry for the late response, thanks for helping me with so many tips. i will keep it in mind when dealing with colab comfy from now on.👍
@BalmoAI no worries, hope it helps! ♥️
Inpainting in IMG2IMG works well. There is a small suggestion, maybe the default setting of "seperate vae" and the node "load vae" could be off and muted initially. Anyway, thank you so much !
With a pony model, I am getting an error in the Sampling process in v5:
- Return type mismatch between linked nodes: scheduler, received_type(['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal', 'bong_tangent']) mismatch input_type(['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal', 'bong_tangent', 'beta57'])I am using dpmpp_sde with normal scheduler.
Does anyone know how I can fix this?
Many thanks!
Got a really stupid question for you...is there a way to turn off the ding at the end? I thought it'd be in the save node, but doesn't appear to be.
TL;DR: My dog is a freak and goes nuts when he thinks there's someone at the door...which this ding triggers, every time a pic finishes. :D Currently, I'm just trying to remember to turn off the speakers, but figured I should ask if there's an easy fix for me forgetting.
(PS, like I said...stupid question)
Thank you for your workflows. I'm running TXT2IMG and IMG2IMG 5.0, and they are so packed with features. It's great how you explain everything, you're doing a huge service for the community.
I was wondering what your recommendation would be for incorporating face swap into your workflow? I typically use InstantID or ReActor when I want to capture a particular likeness, but I'm not sure they would be compatible with your workflow or perhaps even necessary. Might the inpainting in IMG2IMG 5.0 work for this?
I'm using ComfyUI 7.0, front end 1.35.9. Received this error: invalid prompt: {'type': 'invalid_prompt', 'message': 'Cannot execute because a node is missing the class_type property.', 'details': "Node ID '#133'", 'extra_info': {}}
Even though I have RGThree I get the following error:
This workflow uses custom nodes you haven't installed yet.
Label (rgthree)
Mute / Bypass Repeater (rgthree)
Fast Bypasser (rgthree)
Install these nodes to run this workflow, or replace them with installed alternatives. Missing nodes are highlighted in red on the canvas.
I'm testing the most basic generation and I got * KSampler 82:
- Required input is missing: negative
- Required input is missing: positive
Currently, the inputs of KSampler's positive and negative conditioning are from Controlnet process.
There is a node called Anything everywhere prompts which shows Deprecated.
And If i convert all UEs to real links.
The outputs of both positive and negative prompts are empty. I have to connect them myself.
Hi. Unfortunately, I couldn't start the workflow. I get an error.
KSampler 546:82:
- Return type mismatch between linked nodes: scheduler, received_type(['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal', 'bong_tangent']) mismatch input_type(['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal', 'bong_tangent', 'beta57'])
* KSamplerAdvanced 546:576:
- Return type mismatch between linked nodes: scheduler, received_type(['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal', 'bong_tangent']) mismatch input_type(['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal', 'bong_tangent', 'beta57'])
* KSamplerAdvanced 546:575:
- Return type mismatch between linked nodes: scheduler, received_type(['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal', 'bong_tangent']) mismatch input_type(['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal', 'bong_tangent', 'beta57'])
* KSampler 604:537:
- Return type mismatch between linked nodes: scheduler, received_type(['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal', 'bong_tangent']) mismatch input_type(['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal', 'bong_tangent', 'beta57'])
I saw your FAQ about RES4LYF and ComfyUI-ppm, but I don't have those nodes installed. Furthermore, I disabled all my nodes that aren't in your workflow — the result is the same. Any ideas?
Is there an install guide for this? The 4700 custom nodes it installs break absolutely everything, in many different ways when manager tries to grab everything.
Hi, thank you for making this! It was a bit overwhelming at first but I'm starting to get the hang of it. Just have a quick question about prompts. I know I could test this out myself but it would save a lot of time as it takes me a while to get an output. For example, if I added "blue eyes" as a prompt, should I add it to the main prompt, face and eye detailer prompts? Hope it make sense.
Ridiculously good. Somehow blazingly fast with a lot of steps and customizability that make the end result consistently amazing. The batch preview with image filter into additional steps is genius. Thanks for sharing! My new go-to :)
Incredible work flow, excellent directions on the workflow itself. Surprisingly easy to use!
Wow, this is the best workflow i used. Its perfect. Great job.
Everyone, who have a problem, try in terminal:
cd custom_nodes\comfyui_controlnet_aux
pip install -r requirements.txt
and like this on other custom nodes
Probably the best workflow ive tried. Its easy to setup via batchfile and thanks to the comments, easy to understand. 5/5
For some reason all my openpose skeletons are applied backward... Someone suggested inverting R and B channels with a channel shuffler node, but I cant figure out where in the img2img workflow to plug it in.
Manually inverting them and uploading the R > B and B > R inverted image works on the txt2img
Hello, I am encountering a UI rendering issue with several Mixlab nodes (e.g., "Size", "Steps", "Sampler Settings") in the latest version of ComfyUI (v0.9.2 / Frontend v1.36.14).
The Issue:
Upon loading the workflow, these nodes appear completely empty/blank. The expected sliders and input fields are missing.
logs are in the comment
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-01-16 17:46:33.474
** Platform: Windows
** Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
** Python executable: D:\AIsoftware\ComfyUI-aki\python\python.exe
** ComfyUI Path: D:\AIsoftware\ComfyUI-aki\ComfyUI
** ComfyUI Base Folder Path: D:\AIsoftware\ComfyUI-aki\ComfyUI
** User directory: D:\AIsoftware\ComfyUI-aki\ComfyUI\user
** ComfyUI-Manager config path: D:\AIsoftware\ComfyUI-aki\ComfyUI\user\__manager\config.ini
** Log path: D:\AIsoftware\ComfyUI-aki\ComfyUI\user\comfyui.log
Prestartup times for custom nodes:
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-easy-use
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\rgthree-comfy
8.2 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-Manager
Checkpoint files will always be loaded safely.
Total VRAM 16311 MB, total RAM 48618 MB
pytorch version: 2.7.0+cu128
xformers version: 0.0.30
Enabled fp16 accumulation.
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 5060 Ti : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 21878.0
WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.
Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
Found comfy_kitchen backend cuda: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Using xformers attention
Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
ComfyUI version: 0.9.2
ComfyUI frontend version: 1.36.14
[Prompt Server] web root: D:\AIsoftware\ComfyUI-aki\python\Lib\site-packages\comfyui_frontend_package\static
[Crystools INFO] Crystools version: 1.27.4
[Crystools INFO] Platform release: 11
[Crystools INFO] JETSON: Not detected.
[Crystools INFO] CPU: Intel(R) Core(TM) Ultra 7 265K - Arch: AMD64 - OS: Windows 11
[Crystools INFO] pynvml (NVIDIA) initialized.
[Crystools INFO] GPU/s:
[Crystools INFO] 0) NVIDIA GeForce RTX 5060 Ti
[Crystools INFO] NVIDIA Driver: 591.74
Exception in thread Thread-10 (_readerthread):
Traceback (most recent call last):
File "D:\AIsoftware\ComfyUI-aki\python\Lib\threading.py", line 1075, in bootstrapinner
self.run()
File "<enhanced_experience vendors.sentry_sdk.integrations.threading>", line 99, in run
File "<enhanced_experience vendors.sentry_sdk.integrations.threading>", line 94, in runold_run_func
File "<enhanced_experience vendors.sentry_sdk.utils>", line 1649, in reraise
File "<enhanced_experience vendors.sentry_sdk.integrations.threading>", line 92, in runold_run_func
File "D:\AIsoftware\ComfyUI-aki\python\Lib\threading.py", line 1012, in run
self._target(*self._args, **self._kwargs)
File "D:\AIsoftware\ComfyUI-aki\python\Lib\subprocess.py", line 1599, in _readerthread
buffer.append(fh.read())
^^^^^^^^^
File "<frozen codecs>", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xb2 in position 7: invalid start byte
[ComfyUI-Easy-Use] server: v1.3.4 Loaded
[ComfyUI-Easy-Use] web root: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-easy-use\web_version/v2 Loaded
ComfyUI-GGUF: Partial torch compile only, consider updating pytorch
### Loading: ComfyUI-Impact-Pack (V8.28.2)
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[Impact Pack] Wildcards loading done.
### Loading: ComfyUI-Impact-Subpack (V1.3.5)
[Impact Pack/Subpack] Using folder_paths to determine whitelist path: D:\AIsoftware\ComfyUI-aki\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
[Impact Pack/Subpack] Ensured whitelist directory exists: D:\AIsoftware\ComfyUI-aki\ComfyUI\user\default\ComfyUI-Impact-Subpack
[Impact Pack/Subpack] Loaded 0 model(s) from whitelist: D:\AIsoftware\ComfyUI-aki\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
[Impact Subpack] ultralytics_bbox: D:\AIsoftware\ComfyUI-aki\ComfyUI\models\ultralytics\bbox
[Impact Subpack] ultralytics_segm: D:\AIsoftware\ComfyUI-aki\ComfyUI\models\ultralytics\segm
### Loading: ComfyUI-Inspire-Pack (V1.23)
Found LoRA roots:
- D:/AIsoftware/ComfyUI-aki/ComfyUI/models/loras
Found checkpoint roots:
- D:/AIsoftware/ComfyUI-aki/ComfyUI/models/checkpoints
- D:/AIsoftware/ComfyUI-aki/ComfyUI/models/diffusion_models
- D:/AIsoftware/ComfyUI-aki/ComfyUI/models/unet
Found embedding roots:
- D:/AIsoftware/ComfyUI-aki/ComfyUI/models/embeddings
Updated 'comfyui' library with current folder paths
Detected async ComfyUI execution, installing async metadata hooks
Metadata collection hooks installed for runtime values
ComfyUI Metadata Collector initialized
Example images path:
Added static route for locales: /locales -> D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-lora-manager\locales
Registered model type 'lora' with service LoraService and routes LoraRoutes
Registered model type 'checkpoint' with service CheckpointService and routes CheckpointRoutes
Registered model type 'embedding' with service EmbeddingService and routes EmbeddingRoutes
Registered default model types: lora, checkpoint, embedding
Setting up routes for 3 registered model types
Successfully set up routes for lora
Successfully set up routes for checkpoint
Successfully set up routes for embedding
LoRA Manager: Set up routes for 3 model types: lora, checkpoint, embedding
### Loading: ComfyUI-Manager (V3.39.2)
[ComfyUI-Manager] network_mode: public
[ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
### ComfyUI Revision: 4551 [8f40b43e] *DETACHED | Released on '2026-01-15'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
--------------
### Mixlab Nodes: Loaded
json_repair## OK
ChatGPT.available True
edit_mask.available True
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
## clip_interrogator_model not found: D:\AIsoftware\ComfyUI-aki\ComfyUI\models\clip_interrogator\Salesforce\blip-image-captioning-base, pls download from https://huggingface.co/Salesforce/blip-image-captioning-base
ClipInterrogator.available True
## text_generator_model not found: D:\AIsoftware\ComfyUI-aki\ComfyUI\models\prompt_generator\text2image-prompt-generator, pls download from https://huggingface.co/succinctly/text2image-prompt-generator/tree/main
## zh_en_model not found: D:\AIsoftware\ComfyUI-aki\ComfyUI\models\prompt_generator\opus-mt-zh-en, pls download from https://huggingface.co/Helsinki-NLP/opus-mt-zh-en/tree/main
PromptGenerate.available True
ChinesePrompt.available True
RembgNode_.available True
TripoSR.available
MiniCPMNode.available
Scenedetect.available
FishSpeech.available
SenseVoice.available
D:\AIsoftware\ComfyUI-aki\python\Lib\site-packages\ctranslate2\__init__.py:8: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
import pkg_resources
Whisper.available False
fal-client## OK
FalVideo.available
--------------
(pysssss:WD14Tagger) [DEBUG] Available ORT providers: TensorrtExecutionProvider, CUDAExecutionProvider, CPUExecutionProvider
(pysssss:WD14Tagger) [DEBUG] Using ORT providers: CUDAExecutionProvider, CPUExecutionProvider
警告: 无法导入 nunchaku.lora.flux.to_diffusers。ZML_名称加载lora(nunchaku) 节点将无法使用，请确保 nunchaku 库已安装（不使用nunchaku的用户可忽略）。
==================================================
💡 [ComfyUI-ZML-Image] 注册节点总数为: 142！
==================================================
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes\nodes\nodes_list.py:383: SyntaxWarning: invalid escape sequence '\W'
"optional": {"folder_path": ("STRING", {"default": "C:\Windows\Fonts", "multiline": False}),
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes\nodes\nodes_list.py:393: SyntaxWarning: invalid escape sequence '\W'
def make_list(self, source_folder, start_index, max_rows, folder_path="C:\Windows\Fonts"):
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes\nodes\nodes_xygrid.py:256: SyntaxWarning: invalid escape sequence '\R'
resolved_font_path = os.path.join(os.path.dirname(os.path.dirname(os.path.realpath(__file__))), "fonts\Roboto-Regular.ttf")
------------------------------------------
Comfyroll Studio v1.76 : 175 Nodes Loaded
------------------------------------------
** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
------------------------------------------
[D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
[D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False
[D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'MIGraphXExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
DWPose: Onnxruntime with acceleration providers detected
Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success!
[rgthree-comfy] Loaded 48 fantastic nodes. 🎉
[rgthree-comfy] ComfyUI's new Node 2.0 rendering may be incompatible with some rgthree-comfy nodes and features, breaking some rendering as well as losing the ability to access a node's properties (a vital part of many nodes). It also appears to run MUCH more slowly spiking CPU usage and causing jankiness and unresponsiveness, especially with large workflows. Personally I am not planning to use the new Nodes 2.0 and, unfortunately, am not able to invest the time to investigate and overhaul rgthree-comfy where needed. If you have issues when Nodes 2.0 is enabled, I'd urge you to switch it off as well and join me in hoping ComfyUI is not planning to deprecate the existing, stable canvas rendering all together.
Import times for custom nodes:
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\websocket_image_save.py
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui_memory_cleanup
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI_Text_Translation
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mxtoolkit
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-Text-Translation
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\reservedvram
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-WD14-Tagger
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-GGUF
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\cg-image-filter
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-vslinx-nodes
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui_essentials
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI_Qwen3-VL-Instruct
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-advanced-controlnet
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-ZML-Image
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\rgthree-comfy
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-inpaint-cropandstitch
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\wlsh_nodes
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-KJNodes
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui_controlnet_aux
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-QwenVL
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-image-saver
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-custom-scripts
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack
0.0 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\efficiency-nodes-comfyui
0.1 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-impact-subpack
0.1 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes
0.1 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
0.1 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-lora-manager
0.2 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-florence2
0.3 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-Crystools
0.4 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper
0.7 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-Manager
2.4 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-easy-use
2.4 seconds: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes
Context impl SQLiteImpl.
Will assume non-transactional DDL.
Assets scan(roots=['models']) completed in 0.033s (created=0, skipped_existing=161, total_seen=165)
Starting server
To see the GUI go to: http://127.0.0.1:8188
Recipe cache initialized in 0.00 seconds. Found 0 recipes
Lora cache hydrated from persisted snapshot with 73 models
Checkpoint cache hydrated from persisted snapshot with 21 models
Embedding cache hydrated from persisted snapshot with 16 models
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/photoswipe-lightbox.esm.min.js
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/photoswipe.min.css
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/pickr.min.js
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/classic.min.css
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/juxtapose.css
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/model-viewer.min.js
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/juxtapose.min.js
FETCH ComfyRegistry Data: 5/119
FETCH ComfyRegistry Data: 10/119
FETCH ComfyRegistry Data: 15/119
FETCH ComfyRegistry Data: 20/119
data_path: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\data
FETCH ComfyRegistry Data: 25/119
[ComfyUI-Manager] The ComfyRegistry cache update is still in progress, so an outdated cache is being used.
FETCH DATA from: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-Manager\custom-node-list.json [DONE]
FETCH DATA from: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-Manager\github-stats.json [DONE]
FETCH DATA from: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-Manager\extras.json [DONE]
FETCH DATA from: D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\ComfyUI-Manager\extension-node-map.json [DONE]
FETCH ComfyRegistry Data: 30/119
Extracted zip file to D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-videohelpersuite
Install: pip packages
FETCH ComfyRegistry Data: 35/119
[ComfyUI-Manager] Queued works are completed.
{'install': 1}
After restarting ComfyUI, please refresh the browser.
FETCH ComfyRegistry Data: 40/119
FETCH ComfyRegistry Data: 45/119
FETCH ComfyRegistry Data: 50/119
FETCH ComfyRegistry Data: 55/119
FETCH ComfyRegistry Data: 60/119
FETCH ComfyRegistry Data: 65/119
FETCH ComfyRegistry Data: 70/119
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/photoswipe-lightbox.esm.min.js
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/photoswipe.min.css
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/pickr.min.js
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/classic.min.css
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/juxtapose.css
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/model-viewer.min.js
D:\AIsoftware\ComfyUI-aki\ComfyUI\custom_nodes\comfyui-mixlab-nodes\webApp\lib/juxtapose.min.js
FETCH ComfyRegistry Data: 75/119
FETCH ComfyRegistry Data: 80/119
FETCH ComfyRegistry Data: 85/119
FETCH ComfyRegistry Data: 90/119
FETCH ComfyRegistry Data: 95/119
FETCH ComfyRegistry Data: 100/119
FETCH ComfyRegistry Data: 105/119
FETCH ComfyRegistry Data: 110/119
FETCH ComfyRegistry Data: 115/119
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
V5 T2I seems to be broken?
Loop Detected 890,911,546,278,
890 is the HiRes Fix inpaint node,
278 is ControlNet Process
Normally I'd fix it myself but I'm not touching that rats nest of wires.
RGThree also detects it as corrupt and attempts to fix in place, but obviously doesn't succeed, even though it says it does.
No one else getting this?
Thanks for the update! Last time I used your workflow was a few months ago.
The FAQ and guide are so helpful, I wanted to suggest, after using so many adetailer models, some are a little old or have trouble detecting (especially the face ones) I found these to work incredibly good
https://huggingface.co/Anzhc/Anzhcs_YOLOs#face-segmentation
Hi! I just moved to the portable ComfyUI and now I'm running into this problem:
Cannot execute because a node is missing the class_type property.: Node ID '#527'.
I figured it's that 'upscale by factor' node from your node pack. I've tried reinstalling it - both via the manager and manually - several times. I even tried replacing and remapping the node manually, but nothing works.
Here's a log https://pastebin.com/W2qdCX18
Thanks in advance!
Hey @vslinx, quick question for you. In your guide, you stated it's best to use a non-stylized checkpoint during IMG2IMG, and you suggested NoobaiCyberFix for anime. I was wondering if there are any checkpoints you recommend for realistic-style images during IMG2IMG?
"workflowControlNet Models" not found. Can't seem to locate it.
I'm new to this and I can't figure out why I keep getting the same image being created over and over with only tiny changes? I have to edit the pose part of my prompt to make it create a new unique image, but then that one just keeps being recreated?
Tried to solve this problem:
Ksampler: 'NoneType' object is not iterable.
I only use as it is, no much modification.
All models downloaded.
But still no good result.
Tried on/off controlnet still no result.
Tried to replace the Clip Prompt on IMG2IMG TRANSFER BUS also error.
The T2I works fine, but this one.. idk..
Can you help?
Thanks!
# ComfyUI Error Report
## Error Details
- Node ID: 992
- Node Type: KSampler
- Exception Type: TypeError
- Exception Message: 'NoneType' object is not iterable
## Stack Trace
```
File "/workspace/ComfyUI/execution.py", line 518, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
Is this supposed to be easy to use...? Is there any youtube tutorial or something pls
Hey @alesanand97,
this is not a simple or easy workflow - for that there's ton's of easier options here on civitai ^^
This workflow is an All-in-One solution, if you have used Automatic1111's WebUI before and you want the same feature-set, this workflow is most likely your best shot.
It has a lot of knobs and values that make it easy to use for an end-user without having to have a deep understanding of comfyui itself. This is who this workflow is aimed at.
If you don't have any idea what controlnet, ipadapter, hires fix, inpainting, adetailer or refiner is - this workflow is probably a bit too much functionality to grasp at the beginning.
There is no youtube video but there is a guide you can find in the description (or here).
This is for the img2img varient but it mostly explains everything the workflow has to offer and is pretty similar to the txt2img version. The guide is 2-3 versions behind and doesnt include the newest manual inpainting area.
There are also notes inside the workflow that explain the functionality of all user-relevant nodes and the groups directly inside the workflow.
Quick question, what's the Pre-process Image to Pose for? Also what's the diff between that and Load ControlNet Pose? Thanks!
Hey @arimintzu,
in the "Load ControlNet Pose"-Node you can upload a pose that's already prepared for ControlNet, like you can see here.
If you don't already have a Pose for the specific ControlNet, you first need to create a pose image. You can do that by just uploading any image that you want and turn it into a pose by selecting a preprocessor, uploading the image to "Pre-Process Image to Pose" and then activating the preprocessor function together with the controlnet function.
This will turn your image into a pose, which you can see a preview of in the Debug section, and the workflow will then use that pose to create your image.
Probably a dumb question but after a recent ComfyUI update, my generation keeps getting stuck at 46%.
The extension 'CryTools' is also suddenly giving a conflict with this error message:
"GPU/Accelerator not supported (available: CUDA, required: GPU :: NVIDIA CUDA)".
If I search online, people recommend against using CryTools but offer no real solution.
Would you happen to know what's going on?
Hey @MindAddiction,
no worries - there are no stupid questions :D
This is the first time i have heard of this issue, but i have found similar problems on their github repo. What GPU do you have? Is it a non-nvidia or a 50 series?
Seemingly there are fixes for this problem that have yet to be merged but the node hasnt received an update in 5 months, so my hopes are low on that regard.
BUT i have been developing the 5.1 version of the workflow where i mainly make the workflow more stable and remove a lot of unnecessary custom nodes to make the requirements easier.
Crystools was one of these custom_nodes that i have removed from the workflow.
You can find the TXT2IMG 5.1 here and the IMG2IMG 5.1 here.
They are basically done already, there's just one bug i want to iron out in the img2img that's very nieche and probably not really problematic for most people and for the txt2img i'm just waiting for 2 merge-requests being merged in some custom_nodes since they'd make the workflow more performant.
But they are already good to use and should help you fix that problem since they don't use Crystools anymore, so you can delete that node from yours.
@vslinx Firstly, I want to thank you for responding, both so quickly and thoroughly.
It's neither of those two, afaik: NVIDIA Geforce rtx 4070 super
I'll give the 5.1's a try and get back to you.
Also thank you again, I absolutely adore your workflows, and they've really helped me understand this whole thing better.
EDIT: That one seems to work, though it is still slower than it was before the update but no more conflicts is a win in my book. Thank you.
@MindAddiction no need to thank me, usually i'm more active and answer faster :D
But the last few days have been a bit busy.
Weird, maybe you don't have cuda specifically installed, but it should not break the nodes.
I guess i'll roll out the 5.1 in the following days without waiting for the merge-requests since this'll probably happen more often now.
My best guess is that ComfyUI doesn't include CUDA as a dependency by default anymore and Crystools references it ^^
Glad the workflows are helping you!
Sorry that the workflow seemingly got slower :/ My best guess is that they have changed something with the memory allocation. That's sadly not something i have a lot of control over :(
@vslinx The slowness is unintended and not the fault of the workflow. The recent changes with VRAM in ComfyUI somehow crash my computer during the VAE step.
Thank you very much for helping, and I hope you will be less busy in the future, or at least that it is the good kind of busy!
@MindAddiction Yeah i also sometimes have this issue.
Sometimes when comfyui updates i'm running into super long VAE Decode processes, when it'd usually take half a second it all of a sudden takes 40-50 seconds. And that's on a 4090.
And then after another comfyui update it works fine all of a sudden again. Sometimes it's worth not upgrading haha :D
Thank you! Hope your issue get's fixed soon and i hope that the workflow will help you 🫡♥️
@MindAddiction
PS: Was running into the same issue again today, i think the latest comfyui update changed their smart memory logic and it now offloads VAE Decoding onto your CPU instead of GPU when it thinks that you don't have enough vram available.
For me it only happened during the detailers - so you can simply open the Detailer and select "Tiled Encode" and "Tiled Decode" in the Detailer settings, it then does it automatically in smaller chunks and doesn't offload to the CPU.
You can also disable the smart-memory shit globally for comfy by using "--disable-smart-memory" in the starting arguments of your comfy start. You can also force your comfy to always do everything your gpu only by using "--gpu-only".
Neither are super good if you're doing very vram heavy tasks that have to offload to CPU/RAM, like generating videos or something - but it'd help a lot with image generation where you know you have enough vram and comfy is just being dumb with it's smart memory management.
For some reason, after recent update of ComfyUI and some nodes, workflow's save images is not function anymore, I tried to find out which node got problem but failed, is that yet another comfy's update issue or some node conflict?
Heya @155T,
thanks for the report.
Seemingly the newest comfyui update has broken quite a lot of things... 🥲
Not just with my workflow but inside the comfyui frontend in general.
Load image nodes work awfully right now and will empty the preview and output when you switch images or workflow tabs...
I am right now developing my own "load last generated image"-node to use instead of the comfy one, since it has been a painpoint in the past and i think i can do better 😂
I'll release a new version later today, thanks again for bringing this to my attention!
Hi, so for some reason, the "Load last generated image" node is not displaying the images when I click refresh, or when I press the arrows to switch images. When I upload the image through "choose file to upload", it shows it properly, but when I press the arrows to switch between images, it disappears.
Here's an imgur link to a screenshot of what I'm talking about, lest my description is inadequate.
https://imgur.com/a/9GeWotY
This only happened today, I think after my desktop app verison of comfy updated to 0.17.1, so I'm wondering if the update was what broke it, or if it's an issue on my end.
This doesn't really pose too much of a impediment to the TXT2IMG workflow--the image is generated properly, and the image generated are stored to the output folder correctly--Although it refreshes to the correct file name after generation if you have the auto-refresh option enabled, the image is not displayed. Same thing for Manual-inpainting. After uploading the image and editing the mask, the clipspace image that it usually shows also does not show. But otherwise, the image generates and the file is saved as well, so it's not really THAT critical of an issue. It is kinda annoying though.
Moreover, it clears your workflows everytime you launch the app, requiring you to reopen them individually again, but this is just my ranting about this new update that's causing this(?).
Hey @last27683599,
thanks for the report.
Seemingly the newest comfyui update has broken quite a lot of things... 🥲
Not just with my workflow but inside the comfyui frontend in general.
Load image nodes work awfully right now and will empty the preview and output when you switch images or workflow tabs...
I am right now developing my own "load last generated image"-node to use instead of the comfy one, since it has been a painpoint in the past and i think i can do better 😂
I'll release a new version later today, thanks again for bringing this to my attention!