CivArchive
    Preview 116208586

    Note: I spend a lot of time on these to make sure they are top notch. If you have ANY issues, I'm very responsive. hit me up and I'll resolve them for you.

    This is an advanced workflow designed for people familar with Comfyui and who want pro grade results. I encourage you to learn it, but if it is overwhelming, the simple version can be found HERE

    A complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civarchive.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown

    也有中文说明

    Instagram: https://www.instagram.com/synth.studio.models/

    Buy me a☕ https://ko-fi.com/lonecatone

    This represents hundreds of hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip 😉

    There will be no futher updates with Face Swap or Reactor in them. I have removed them completly.

    V12.1

    • Added an Inpaint area

    • Modified controlnet so it doesn't fault out if a mask isn't loaded without resetting teh switch

    • Removed the sentence remover (it sucked)

      • added "banned tag remover" at the metadata saver so you can still process normally

    V11.1.2

    • Updated 📝Prompt Assist

    • Updated ⚙️ main area

    • Added back Qwen VL prompt enhancer (now that it's fixed)

    • Updated 🔎 detailers

    • Updated 💾 Save area so that you can embed workflows as well as add a simple date to the folders so you aren't endlessly looking for them.

    • Added an inline ✂️ crop tool in the 🎨Post Production Suite

    Ver 10

    • Improved regional prompt suites

    • Added IP Adapters for Face, style, and composition for Facial and pose consistency

    • Improved detailer suite

    • reworked settings for easier use

    • Added CivitAI sentence ✂️

    Ver 9.0

    • Qwen nodes keep getting mbroken due to updates. I removed them in V9

    • Removed outdated sections

    • Added a 2nd KSampler & model option for refinement

    • V 8.1 is included in the folder

    VER 8

    • Created a really cool regional prompter.

    • Works with controlnet

    • Upgraded detailers to accomodate for it so you can detail each face seperately


    This is an all in one workflow:

    • Controlnet: background remove, canny, openpose, depth, canny/depth

    • I2I prompt assist

    • QwenV2 Prompt enhancer.

    • Florence and Qwen prompt assist

    • Style selector

    • Dual Model Loader: Better control

    • Sage Attention: Speeds up production

    • Ultimate Upscaler for prescaling and hi res fix

    • Detailing Suite for face, hands, eyes, and expressions

    • multi face detailer

    • Seed VR2 Upscaler to get 4k on low VRAM

    • Massive Post Production Suite

    • Smart Noise scrubber

    • Full tutorial available.

    • 也有中文说明

    Description

    • Upgraded Post Processing Suite.

    • Reworked the control area.

    • Reworked the Controlnet.

    • Massive addition to notes and instructions.

    FAQ

    Comments (9)

    aer233Jan 10, 2026
    CivitAI

    Thanks for this awesome workflow! I met the Failed to restore node: Ultimate SD Upscale
    Please remove and re-add it.

    The parameter for

    UltimateSDUpscale

    is offset by one.

    The comfyui and UltimateSDUpscale is both latest and cannot fix the issue after reinstalling.

    I manually checked the workflow json file, and founds that deleting the "randomize" could make it work

    "widgets_values": [ 2, 688326192026688, "randomize", 4, 1, "deis", "simple", 0.15, "Chess", 512, 512, 8, 32, "None", 1, 64, 8, 16, true, false ],

    lonecatone23
    Author
    Jan 10, 2026

    I've never had that node fail. It's a standard one. Super odd.

    What platform are you on?

    lonecatone23
    Author
    Jan 10, 2026

    Try unplugging the sliders that control teh scheduler and sampler.

    1648003234289Jan 23, 2026
    CivitAI

    thanks for your works!
    But I got some mistakes when i tried to use it, the following comment were the erro output from the comfyui:
    Prompt outputs failed validation:
    Required input is missing: images FaceDetailer:
    - Required input is missing: vae
    - Required input is missing: model VAEDecode:
    - Required input is missing: vae FaceDetailer: - Required input is missing: vae
    - Required input is missing: model FaceDetailer: - Required input is missing: vae
    - Required input is missing: model VAEDecode: - Required input is missing: vae KSamplerAdvanced: - Required input is missing: model SaveImage: - Required input is missing: images
    ==================
    These errors occurred when I tried to use this workflow to make I2I creation. Really need your help~
    By the way, is there any guide video for this workflow? Honestly, artical guid dealt with all the installing issues, but really hoped for the following trail. Thamls~

    1648003234289Jan 23, 2026

    Addition, I swerved I do not modify any node connect. Thanks for your help.

    lonecatone23
    Author
    Jan 23, 2026

    Above the empty white 'Note' box in the user input is an "anything everywhere" node. make sure the VAE is connected to it. It is black and from top to bottom shoud say "Clip, VAE, Model". I have no idea why that is not hooked up as it is on the version I uploaded.

    The "save image" error is prpobably in teh save group. It'll circle it in red. I'd need to knwo wheich node. More than likely you have somethign turned off and that turned on (Like the mask)

    1648003234289Jan 23, 2026

    @lonecatone23 
    Thanks for your comments guide~
    Honestly, I have no idea why you update file version do not connect these (vaes+modules) to the target nodes, so that I connect them manually (lol).
    I don't know if it is real coherence with your original version which is right, but it is works~
    By the way, I have followed your account, very appreciate~

    1648003234289Jan 23, 2026

    @lonecatone23 
    Well, I really hope this workflow can hold a video guide~