Consistent Character Creator v01
Table of Contents
---
Overview
The Consistent Character Creator v01 by Mickmumpitz is a ComfyUI workflow that makes generating character sheets for AI art automatic.
Starting with either Flux or SDXL, the workflow transforms a single character image into a complete set of high-resolution views from different angles, with customizable expressions you can adjust using sliders, and various lighting conditions.
Everything gets automatically arranged into two different character sheet formats, making it simple to share your characters or track your progress, and the output is perfect for training custom AI models for AI movies, comics, or branding.
There are three versions of the Consistent Character Creator workflow.
- ConsistentCharacterCreator_Flux (best Quality, very slow, System-intensive)
- Low Vram Version
- ConsistentCharacterCreator_SDXL (good quality, good speed)
- Low Vram Version
If you support me on Patreon you can also get the advanced versions of these workflows with additional upscalers and example files.
👉 I recommend starting with the SDXL version for fast iteration and good quality.
Versions
This guide documents the primary variants of the Consistent Character Creator workflow:
- ConsistentCharacterCreator_Flux (best Quality, very slow, System-intensive)
- Low Vram Version
- ConsistentCharacterCreator_SDXL (good quality, good speed)
- Low Vram Version
Recommendation
👉 I recommend starting with the SDXL version for fast iteration and good quality.
Installation
1. Install ComfyUI
1. Download ComfyUI: https://github.com/comfyanonymous/ComfyUI
2. Extract the folder to the location where you want to install ComfyUI.
3. Install Git: https://git-scm.com/download/win
- standalone version (follow the standard installation steps)
4. Download ComfyUI Manager: https://github.com/ltdrdata/ComfyUI-Manager
5. Right-click on the download link > “save link as” > navigate to your ComfyUI folder and download.
6. After it is done, double-click the manager to install it.
7. After it’s done you can run ComfyUI by clicking run_nvidia_gpu.
Congratulations, you installed ComfyUI! 🥳 To use my workflows you’ll need some extra models and extensions, but it is super easy to install them!
SDXL & SDXL LowVram
Drag & drop into the SDXL workflow and install missing custom nodes.
Download these models and put them in the corresponding folders:
Checkpoint: https://civitai.com/models/133005/juggernaut-xl
📁 ComfyUI_windows_portable\ComfyUI\models\checkpoints
!
You can also use any other SDXL checkpoints for all the workflows. You can find more models on CivitAI.com.
Check the example images for the settings and match them in your KSampler!
SD15 Checkpoint: https://civitai.com/models/84728/photon (needed for IC-Light)
📁 ComfyUI_windows_portable\ComfyUI\models\checkpoints
CONTROL NET: xinsir/ControlNet++: All-in-one ControlNet (ProMax model)
📁 Open the ComfyUI Manager > Model Manager > search for “promax” > install
UPSCALE MODEL: https://openmodeldb.info/models/4x-ClearRealityV1
📁 \ComfyUI_windows_portable\ComfyUI\models\upscale_models
IP ADAPTER: Open the ComfyUI Manager > Model Manager > search for “ip adapter” > install all the ones that have “You can use this model in the ComfyUI IPAdapter plus extension.”
You don’t need all these models for this workflow, but it is good to have them all for future use. Check out: https://github.com/cubiq/ComfyUI_IPAdapter_plus
Go into the model manager and search for “ipAdapter”. Install these models too:
- ip-adapter_sdxl_vit-h.safetensors
- ip-adapter-plus_sdxl_vit-h.safetensors
- ip-adapter-plus-face_sdxl_vit-h.safetensors
CLIP VISION: You can find these in the manager! Search for “Clip”.
- CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
- CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors
📁 /ComfyUI/models/clip_vision
IC-LIGHT: Open the ComfyUI Manager > Model Manager > search for “ic light” > install
- iclight_sd15_fbc
BBOX_DETECTOR: Open the ComfyUI Manager > Model Manager > search for “bbox” > install
- face_yolov8m (bbox)
FLUX
Drag & drop into the FLUX workflow and install missing custom nodes.
Download these models and put them in the correct folders:
FLUX CHECKPOINT:
📁 ComfyUI_windows_portable\ComfyUI\models\checkpoints
SD15 CHECKPOINT: https://civitai.com/models/84728/photon (needed for IC-Light)
📁 ComfyUI_windows_portable\ComfyUI\models\checkpoints
SDXL Checkpoint: https://civitai.com/models/133005/juggernaut-xl (needed for MV Adapter)
📁 ComfyUI_windows_portable\ComfyUI\models\checkpoints
CONTROL NET:
📁 Open the ComfyUI Manager > Model Manager > search for “promax” > install
UPSCALE MODEL: https://openmodeldb.info/models/4x-ClearRealityV1
📁 \ComfyUI_windows_portable\ComfyUI\models\upscale_models
* You can also use other upscale models like 4xUltraSharp which you can download via the ComfyUI Model Manager.
IC-LIGHT: Open the ComfyUI Manager > Model Manager > search for “ic light” > install
- iclight_sd15_fbc
BBOX_DETECTOR: Open the ComfyUI Manager > Model Manager > search for “bbox” > install
- face_yolov8m (bbox)
IC-LIGHT, CLIP, and DETECTION Resources
- CLIP VISION: You can find these in the manager! Search for “Clip”.
- CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors,
- CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors
- IP Adapter models listed above
- BBOX_DETECTOR model listed above
Troubleshooting
ERROR 1 - Failed to install custom nodes
I had the problem that with the new version of ComfyUI some custom nodes are not installed correctly. This was due to an incorrect version of huggingface hub.
To fix this, open your ComfyUI folder (where “run_nvidia_gpu” is located), click on the address bar and type “cmd” > Enter.
Now copy this command:
python_embeded\python.exe -m pip install --upgrade huggingface_hub
and press “Enter”. When it's done, restart ComfyUI.
ERROR 2 - STILL failed custom nodes
Thank you to my Discord User “Foltin” creating this workaround:
“I think I figured out how to install everything properly. You don't need all these models for this workflow, but it is good to have them all for future use. Check out: https://github.com/cubiq/ComfyUI_IPAdapter_plus
1. run update_comfyui_and_python_dependencies.bat
2. in the python_embedded folder, type “CMD” into the address bar to open the command window and run these:
python -m pip install --upgrade streamdiffusion
3. python -m pip install --upgrade diffusers
4. python -m pip install --upgrade huggingface_hub
5. python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu124 --force-reinstall
6. python -m pip install xformers==0.0.29.post2
The important part is that you have to update torch again after updating huggingface_hub and diffusers because they mess up torch.”
ERROR 3 - Could not run 'torchvision::nms' with arguments from the 'CUDA' backend
This might happen with newer ComfyUI Versions while using Face Detailer.
To fix this, open your ComfyUI folder (where “run_nvidia_gpu” is located), click on the address bar and type “cmd” > Enter.
.\python_embeded\python.exe -m pip install --force-reinstall torchvision --index-url https://download.pytorch.org/whl/cu121
and press “Enter”. When it's done, restart ComfyUI.
ERROR 4 - My MV Adapter Output is just a blurry mess
Make sure you are using the correct pipeline:
ERROR 5 - Expression editor not working
You probably just need to put in 1.5 as crop_facter where it says NaN. This is a weird bug that happened after a recent update.
[Images in the guide show example pipelines and UI contexts to help resolve these issues.]