🛠️ Purpose & Design Philosophy
This workflow is a high-fidelity environment built for Illustrious. It prioritizes stability and professional texture over generation speed. It follows an "all-in-one" philosophy: configure your prompts, hit queue, and let the workflow handle the multi-stage refinement from start to finish.
Not for Speed: This is a heavy-duty refinement tool. If you want 2-second previews, use a basic workflow.
Personal Use: Built for my specific production needs. It is shared as-is for those who want a "set-and-forget" pipeline for Illustrious. Adjust the settings and models to fit your needs. The defaults on v19+ will be what I used for the sample images.
All-in-One Logic: The workflow handles generation, detailing, and upscaling in one continuous pass.
If you're needing something with more features: Try checking out Silly All-in-one, Multiple Characters With Regional Loras which is on civitai. I have no plans to implement additional features.
⚠️ Disclaimer & Compatibility
Install at Your Own Risk: Custom nodes can break your environment. I am not responsible for troubleshooting your specific installation.
ComfyUI: Built and tested on the non-app version. Desktop app users may face additional hurdles.
The "Your Version" Factor: Your node versions and environment are 99.9% likely to differ from mine.
Nodes 2.0: I do not recommend using Nodes 2.0. It creates unpredictable UI behavior; I will not provide support for issues involving this feature.
🤝 Support & Boundaries
I have not and never will monetize my workflow. CivitAI is the only platform I am maintaining this workflow on. If you find a version of my workflow posted and/or monetized anywhere and use it, then whoever posted it is responsible for providing you any support. This is the main reason why I don't monetize this: I don't want to be or feel obligated to provide support.
No DMs: DMs are disabled due to repeat spam. Please check the Discussions tab below; most questions have already been answered.
Modifications: You are free to hack this workflow apart. However, you are responsible for fixing it if it breaks.
Custom Requests: I do not make private workflows. If you need a custom solution, post a Bounty on CivitAI. There are many talented creators ready to help you for a fee.
Description
This is an example of an IMG2IMG workflow and should work for anyone as long as they have the related custom nodes:
By my standards, this workflow is super simple and basic. It performs IMG2IMG and then upscales. That's it.
As always, settings will need to be adjusted to fit your needs.
Looks like the Comfy Core "Save Image" node does not save the prompt (for me). Just FYI that you will have to add your prompt when uploading.
FAQ
Comments (11)
Added a simple (to me) IMG2IMG workflow. Sample images will be shown whenever moderation releases them from review.
looks like the default comfy core save image node doesn't save the prompts in a format that civitai can read (for me), just FYI
My guess is this is because there is no KSampler in the workflow. I am pretty sure the prompt populates when using my Simple V2 workflow.
Have a preliminary version of this with Image Saver. IDK about anyone else, but I don't like have to do a bunch of stuff manually like adding resources, prompts, etc.
Will upload soon.
I wanted to add more adetailer steps.
Where does the (Positive, Negative, Vae and model) Attach to? I suppose the vae and model are the checkpoint and positive are the adetailer boxes you added?
Model input is connected to the ZeroStarCFG output.
VAE input is connected to the "VAE Source Switch" output.
Positive input is connected to the Conditioning (Concat) output.
Negative input is connected to the CLIP Text Encode (Negative) output.
The "boxes" are connected to the wildcard spec field toward the bottom of the detailer nodes.
You can always disconnect stuff and connect them whatever way you want.
I really appropriate your help and giving me your time.
Wonderful workflow, feels better than using Auto1111 with extensions!
So thanks for this =)
@Gladas Last question, not an issue with the workflow but Adetailer.
I'm getting a dumb issue with the face Adetailer. Where the facial tones of anime characters are getting changed. Mostly becoming too unnaturally white. Any suggestions on what to write or adjust in the adetailer? As to improve the face details but not affect the structure or skin tone.
@OctaLoc I run into this as well. You can try adjusting the max size and/or the guide size up, but It will cause the detailer to take longer. I think someone recently said they use an upscaler for faces instead of detailer. Might be worth looking into.
You can also try prompting in the Detailer Helper prompt box for the face detailer. I never really tried adding quality tags there, so might be worth a shot. I'll try it later after work today.
Tried it out and tbh the difference wasn't too noticeable for me, but I generally only do anime style images.
According to Google, the prompts in the wildcard spec box do not override the positive prompt, but they do enhance it. So it's basically like using concat conditioning I guess.
I am by no means a FaceDetailer expert either, so just take what I say with a grain of salt!