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
v2 has better overall usability!
It's recommended to hide link visibility for better clarity. (eye icon in bottom right corner of comfyui)
Easier overview and accessibility of sampler settings
Better control over Processes and optional parameters
Added optional detailer prompts
Added optional detailer LoRA's (recommendations inside note in workflow)
Added Clip Skip slider to switch between 1 or 2 (Some models use Clip Skip 1)
Swapped cg-image-picker with cg-image-filter since the picker is now deprecated
The Workflow now has color coded node-groups. These let you know which group is responsible for which task. The colors mean the following:
Blue/Purple: Preperation, here you have to prepare the workflow. Select your Models, LoRA's and enter your optional detailer prompts.
Green: Image Control, here you change the sampler Settings, select which tasks to run and enter your image prompts.
Orange: Image Generation, here you see previews of your images and your image is being saved. There is an additional Group for debugging to check how and what has been upgraded by the Detailer. This helps to find the cause of issues if your upgrade doesn't end up the way you want it to.
Black: Backend/Technical, here you have all the nodes that do the magic in the background. In an ideal world you'll never have to bother with these unless you know what you're doing and want to tweak the ranges at which the detection and detailers work.
FAQ
Comments (21)
Hello again! I have really enjoyed your workflow! Thank you for making it! In the latest iteration, I am having an issue with the "Is V-Pred Model," I can't seem to download the PrimitiveBoolean node. It says my version of Comfy-ui cannot install it because it is outdated, even though it is up to date. I'm sure this is an issue on my end but I was wondering if you know anything about this issue. Thank you :)
Heya @scottegg472795 ! Very happy to hear that you‘re enjoying the workflows, it‘s usually hard to get feedback on those so i really appreciate comments and questions ^^
It might be the other way around, that the node you‘re trying to install is not compatible because it‘s too old or deprecated.
Which custom node are you trying to install the primitive boolean from? I have attached all the necessary custom nodes in the description (there‘s a v2 requirement list underneath the original one) and also one inside of a note in the workflow itself. Those were all the custom nodes that comfyui said were custom, if you have all of these installed and it still says that the primitiveboolean node does not exist it might be that i have forgotten once of the required nodes. If that is the case it‘d most likely be the node from Crystools:
https://github.com/crystian/ComfyUI-Crystools?tab=readme-ov-file#utils
Please let me know if it worked with just the required nodes and if not, if the crystools helped.
In case neither of these helped i‘ll also check my workflow again once i‘m home in around 7~ hours and will let you know exactly which custom node the PrimitiveBoolean is part of! :)
Hello! I believed I was missing PrimitiveBoolean from Crystools, but it seems that I have it downloaded, and I can place it within the workflow. It appears that I am missing something from comfy_core. I tried to use comfyui manager to download the missing nodes that are in the "Is V-Pred Model" located in the model backend area of the workflow, but I get this error:
"Failed to find the following ComfyRegistry list. The cache may be outdated, or the nodes may have been removed from ComfyRegistry.
comfy-core"
@scottegg472795 Hey, i checked again now that i'm home and like you've said it's not actually a node from the Crystools but from the comfy-core itself. Which is also why it didn't appear in the custom nodes list as it's a default node from the comfy installation.
If you're missing the node it means that either your comfyui is not up-to-date or the installation is somehow broken. Which comfyui version are you using? I'm running on v0.3.27 and ComfyUI Manager on v3.27.11
If you let me know which version you have i can install a clean version of it and try it in a sterile environment
@vslinx I am using comfyui v0.3.27 and comfy ui manager v3.30.3
@scottegg472795 hmmm that's weird.
I have now installed a new clean comfyui installation with your exact version parameters and it's working fine with only the custom nodes i've mentioned installed.
Can you try updating your ComfyUI-Manager node? the newest version should be 3.31.9
Otherwise could you give me the log from your comfyui process? There might be some other issue that could prevent the workflow from loading correctly. If it's a bit longer you could upload it to https://pastebin.com/ and give me the link :)
@vslinx I updated my ComfyUI manager node to 3.31.9, but the issue persists. I have uploaded the terminal log upon loading Comfy Ui and after queuing.
@scottegg472795
Weird, ID#160 is definitely the PrimitiveBoolean node from comfy-core.
It might be that the cached nodes of your comfyui instance are having some issues.
Can you click the two buttons to the right of the Star in the Taskbar at the top?
One says "Unload Models" and the other says "Free model and node cache". Then refresh the page and please try downloading the workflow from civitai again and try to import it again.
If the newly downloaded workflow does not work, can you try this?
https://www.mediafire.com/file/epc6tckks9itmly/vslinx-FaceDetailer-v2.json/file
If that did not work, does this one work?
https://www.mediafire.com/file/lyh1wlhrzszydpg/vslinx-FaceDetailer-v2.1.json/file
And if that does not work either, i made a version with the Crystools primitive boolean instead for you.
This should definitely work for you:
https://www.mediafire.com/file/fokcjdw3embdwgi/vslinx-FaceDetailer-v2.2.json/file
I know it might be annoying to try these 4 things, but you'd help me greatly if you could try them and let me know which workflow worked, the issue might also be caused by how i saved/exported the workflow 🫡♥️
@vslinx I cleared the cache, unloaded the model, and refreshed comfy ui, but nothing changed. V2 and V2.1, didn't work for me, but 2.2 did. I really appreciate the work around workflow you made, you didn't have to do that :). Thank you. I don't mind helping you with your workflows, don't worry about it being annoying!
@scottegg472795 Damn that sucks! I don't know why the default doesn't work.
It might have something to do with using comfyui-portable that you're using, it could be that the portable version doesn't have all the nodes by default that normal comfyui has. But that's just a wild guess.
I'm glad that the workaround works for you though! I will update the Workflow now to v2.1 since i've checked everything thanks to you again and noticed that the original "workflow used" from comfyui wasn't perfectly working and forgot to include 4 needed nodes, namely speaking:
rgthree-comfy (https://github.com/rgthree/rgthree-comfy)
ComfyUI-Crystools (https://github.com/crystian/ComfyUI-Crystools)
Comfyui-ergouzi-Nodes (https://github.com/11dogzi/Comfyui-ergouzi-Nodes)
ComfyUI-Image-Saver (https://github.com/alexopus/ComfyUI-Image-Saver) (i accidentally used an older unsupported version)
So since Crystools is needed anyways for some of the visual nodes i'll change the boolean to the crystools one so that in the future nobody should have this issue anymore! :) Thank you very much for your testing ^^
It helps a lot to have someone test them in a different environment, especially since this is my first workflow ever :D
@vslinx no worries! I am happy to help.
@scottegg472795 The new version 2.1 should be up now! (After some issues with civitai having server problems again)
It should work out of the box with all required nodes installed :D
https://civitai.com/models/1297813?modelVersionId=1593040
@vslinx Hello! Sorry to bother again, but I couldn't find the toggle for the general Loras in the second row. The Loras for specific body parts and detailer Loras have their toggles, but I had to go to the node map to toggle the general ones (they function as intended). Am I missing something or is it not present? Thank you again! 😅
@scottegg472795 Heya, i removed it because it‘s most likely that if you turn them on/off you‘d be changing the model of the lora itself. I didn‘t want to clutter the selector area even more with what felt like useless nodes ^^
You can easily un-bypass any node by simply rightclicking and then clicking „bypass“ at the bottom or by clicking on the node and then pressing Ctrl+B. I felt that this was easier and faster than changing a lora and then having to scroll up into the control area and activating/deactivating them.
@scottegg472795 Heya again! :D
I have brought back the LoRA selector in the new v2.2, amongst other things i've also added easier prompt management. So you can just add Start and End quality prompts like they're often used in noobAI and derived Checkpoints :)
Also the image-saving is way better now and directly saves necessary information for civitai into the img so that the auto-recognition of prompts and sampler settings actually work.
the ergouzi nodes are no longer required but i've implemented some features that require the ComfyUI_Comfyroll_Nodes.
I hope you'll enjoy the new version and that it helps you with your images in the future! Your feedback has helped me a lot to improve the workflow 🫡
@vslinx That's great, thank you :)! For some reason, when I downloaded the workflow, start quality prompt and end quality prompt couldn't be found, however, it worked perfectly normal when I used the gallery image's metadata. And forgive me, but I am unfamiliar with the start and end quality prompts. Are they a way to separate the main prompt from the beginning tags?
@scottegg472795 Oh that‘s weird, maybe the workflow is so big now that comfyui doesn‘t save it anymore :/
Most noobAI Checkpoints recommend to use quality prompts in the front and back of the prompt (masterpiece, very detailed etc.) and this helps to more easily prompt. Since the quality prompts usually never changes you can just leave them as is and when prompting yourself or when copying prompts from civitai you can simply copy the parts that describe the actual scene and paste them instead of having to remove parts of the prompt beforehand or afterwards to fit your checkpoint’s recommendations. You don‘t have to use it at all though, you can simply use the normal middle positive prompt and deactivate the two quality prompts via the control center
@vslinx Oh, that's convenient! I always found it frustrating to add the quality tags when making a new prompt, I didn't know separating them was possible!
@scottegg472795 happy to hear that! i always found it annoying so i thought it might help others :D
I had to do some gymnastics with the prompt fields but you can always check how the prompts come out in the Debug section under "preview prompt". 🫡
@vslinx Sorry for asking so many questions! I recently switched from Automatic1111 to Comfy-UI and everything is new to me.
@scottegg472795 No worries! i appreciate the questions and i'm sure other people have some too :D so it helps everyone i think.
I also switched from A1111 to ComfyUI only 3-4 Months ago because A1111 couldn't keep up with newer image gen's and video generation ^^ once you get the hang of it there's really no limitations!