ComfyUI Detailer(ADetailer) All-in-One [Illustrious, Pony, SDXL]

v2.0 (TXT2IMG)
vslinx
6 months ago

ComfyUI Detailer/ADetailer Workflow

Update (v2): The new Requirements(Custom-Nodes) are in the Workflow itself as well as in this Description under "Requirements (v2)".
I had to swap the cg-image-picker with the cg-image-filter because the image-picker is no longer being maintained and therefore deprecated and not compatible with newer comfyui versions.

I wasn't really satisfied with most of the Detailer Workflows because they either were too complicated for no reason or didn't had enough options out of the box.

This is why i've created my own Workflow that lets you generate a batch of however many images you want, select the images you'd want to upscale & improve the details and then see a preview of before & after.

Every Group of Actions is selectable, meaning you can decide if you'd like to upscale, use v-pred model, save the result and select/deselect every single ADetailer by a simple yes/no selector.

Every Part in the Process is optional and it will always work as long as you keep "Models & Setup", "Sampler Settings" as well as "Prompts" enabled.

Requirements (v1)

ComfyUI Impact Pack (https://github.com/ltdrdata/ComfyUI-Impact-Pack)

ComfyUI-Custom-Scripts (https://github.com/pythongosssss/ComfyUI-Custom-Scripts)

cg-use-everywhere (https://github.com/chrisgoringe/cg-use-everywhere)

cg-image-picker (https://github.com/chrisgoringe/cg-image-picker)

ComfyUI Impact Subpack (https://github.com/ltdrdata/ComfyUI-Impact-Subpack)

Requirements (v2)

ComfyUI Impact Pack (https://github.com/ltdrdata/ComfyUI-Impact-Pack)

ComfyUI Impact Subpack (https://github.com/ltdrdata/ComfyUI-Impact-Subpack)

ComfyUI-mxToolkit (https://github.com/Smirnov75/ComfyUI-mxToolkit)

ComfyUI-Easy-Use (https://github.com/yolain/ComfyUI-Easy-Use)

ComfyUI-Custom-Scripts (https://github.com/pythongosssss/ComfyUI-Custom-Scripts)

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)

cg-use-everywhere (https://github.com/chrisgoringe/cg-use-everywhere)

cg-image-filter (https://github.com/chrisgoringe/cg-image-filter)

rgthree-comfy (https://github.com/rgthree/rgthree-comfy)

Requirements (v2.2 and above)

ComfyUI_Comfyroll_Nodes (https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki)

Otherwise same Custom-Nodes as v2 but you can remove Comfyui-ergouzi-Nodes

How to use

Select all necessary models, go down to the Detailer Groups and open the "UltralyticsDetectorP"-Node and select the corresponding Detector-Model for the Body-Part.
You will find my recommended Detection-Models in the Workflow itself or here under "Suggested Resources".

Go to the "Detailer Selector" in the upper area and choose your options.

Only required Groups are Models & Setup, Sampler Settings and Prompts, the rest can be bypassed without compromising the functionality.

If you have a V-Pred Model please activate the "Enable V-Pred Model"-Option to generate images.

You find all Information on how to improve your Details further inside of the "How to improve further"-Note inside of the Workflow.

For v2 check the "How to use"-Node inside the Workflow itself.

Feedback

I'd love to see your feedback or opinion or 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. I'm a big fan of the image picker extension because i can select the best images out of a batch to continue working with and if the result is not to my liking i can easily use the extension as a kind of "img2img" node because i can tweak some settings, enable/disable some detailer's and then select my desired images again and start another upscaling&detailer round by simply selecting the images and hitting "Progress selected image as restart".

Read more...
Download (47.9 KB) Download available on desktop only

Popularity

600 ~10

Info

Base model: Other

Version v2.0 (TXT2IMG): 1 File

To download these files, please visit this page from a desktop computer.

About this version: v2.0 (TXT2IMG)

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.

19 Versions

😥 There are no ComfyUI Detailer(ADetailer) All-in-One [Illustrious, Pony, SDXL] v2.0 (TXT2IMG) prompts yet!

Go ahead and upload yours!

No results

Your query returned no results – please try removing some filters or trying a different term.