🛠️ 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
FAQ
Comments (7)
Fantastic work!!
How difficult would it be to incorporate an I2I build/element to this workflow?
Many thanks for a great piece of work.
Hi, thanks for the compliment!
Regarding I2I:
It's not hard, but not one I would publish since it almost always causes problems for some people. I had it implemented a few times and literally always someone ran into issues from it.
The simplest way is to do it:
1. Add a Load Image node
2. Connect it to something that can convert it to SDXL size
3. Convert to latent via VAE Encode and connect to the SamplerCustomAdvanced latent input
There's other ways to do it, but that's probably the simplest way.
Getting scheduler mismatch error so I disconnected the sampler scheduler settings node from all the Ultimate upscale sampler nodes and it worked. Probably because of comfy updates....Great job btw I've been trying out your workflows for like a year and half now....Great stuff!
Thanks. Yeah, I'm not sure why the scheduler related issues happen for some folks. I'm glad you figured out a workaround!
"Well, I have the same error and the solution worked. Here, by the way, is the log with the error. BasicScheduler 93: - 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']) UltimateSDUpscaleCustomSample 17: - 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']) Output will be ignored
@NoFriend7851766 The fix for someone else was related to a custom scheduler they had installed. Uninstalling the custom scheduler fixed it for them. You have that exact scheduler they mentioned: beta57.
bong_tanget might be okay, but beta57 it for sure does not like based on my interpretation of that error message:
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'])
Disconnecting the node like you did: is the fix if you want to keep that scheduler installed on your local install.
Confirmed that it is related to RES4LYF. I installed it and immediately got that error. What's does not make sense to me is that the Basic Scheduler node ONLY on the USDU nodes get the error too, but not on the initial SamplerCustomAdvanced node.
BasicScheduler and USDU both have beta57 in their dropdowns on the actual nodes, so yeah it's basically something weird with RES4LYF and USDU.
I was going to change the workflow to leave the Sample Scheduler settings node out, but NOPE it's not worth the effort to me. I don't use RES4LYF. The schedulers from RES4LYF don't even register on the FaceDetailer nodes for me, so this is probably related to the some of the issues people had with the Impact Scheduler Adapter node as well.