🌸 KiraNugget's Multiview Character Sheet V1.0 🌸
Turn One Image Into a Complete Character Reference.
Input a single image of your character and instantly generate a full multi-angle character sheet ready for art, animation, 3D modeling, or future generations.
✨ Why You’ll Love It
🖼️ Input just one image
🔄 Automatically recreates your character from multiple angles
😀 Includes multiple facial expressions and close-ups
🎨 Keeps the design consistent across every view
⚡ Minimal setup — no complicated prompting required
⚡ What It Creates
From a single reference image, the workflow generates:
Front views
Side views
Back views
Three-quarter views
Face close-ups with multiple expressions
Bonus portrait image
Bonus landscape / cinematic image
All while preserving your character’s:
Hairstyle
Outfit
Colors
Facial features
Overall style and personality
✏️ Fully Editable
Every section of the sheet can be customized individually with your own prompts.
Want:
A different pose for the side view?
A different expression in one close-up?
A unique outfit, background, or camera angle for the bonus images?
Each panel can be edited separately while still keeping the overall character design consistent.
🎭 Expressions Included
Your character isn’t just recreated from different angles — they also come to life with multiple expressions such as:
Happy
Angry
Sad
Surprised
Smug
Neutral
Perfect for making your character feel more complete and usable.
🧠 Smart Consistency
The workflow is designed to maintain:
Consistent proportions
Matching clothing details
Stable colors and accessories
Accurate facial structure across every angle
No more manually trying to redraw the same character from scratch.
🎨 Perfect For
Character reference sheets
Original characters
Anime and game design
3D modeling references
Comics, VTubers, and visual novels
Training datasets or future image generations
🚀 Bonus Images
In addition to the main sheet, the workflow also creates:
A polished portrait-style image
A cinematic landscape shot of your character
Great for thumbnails, profile pictures, or showing off the final design.
❤️ One Character. Every Angle.
Drop in your favorite character image and let the workflow build the full reference sheet for you.
Because one image should be enough.
Description
V1.0 Release
FAQ
Comments (11)
Looks like an interesting wf, but this part puzzled me: Component-only models (without a main model file) require at least 2 required components... what are the components required?
it was the error message i was getting when trying to upload the workflow. will remove this.
@KiraNugget oh, got it, thanks for the wf!
nunchaku custom nodes are broken AF. At least at the moment. Can't install them. Can;t use the WF.
nunchaku is only 2 nodes, you could always replace them with a regular diffusion model loader and lora loader until nunchaku works. Knowing this, I will place a model switch in my next qwen workflows.
@KiraNugget Sorry for the late reply. Been busy. Normally I would have tired something sane like that. It's just that I had hit a point where it seemed everything I was trying out in the passed few days had been a rats nest (not that yours was) of borked dependencies, and I just gave up. I actually deleted my entire Stability Matrix folder not too long after that to start fresh. I'll probably circle back around soon. I just have that whole busy thing I can't seem to get away form XD.
Hello, I love your workflow. However I cannot make it past the Nunchaku issues specifically the DiTLoader. Can you post a version that will work. Thank you :) <3
For a quick fix; delete nunchaku DiT loader and nunchaku lora nodes and replace with a regular load diffusion model and lora loader, Use your favorite qwen model and loras from there. I will not be updating anything this week as I got a new full time job. Sorry for the inconvenience,
If you’re having trouble installing Nunchaku custom nodes using the Author Workflow, or if the nodes still show errors after installation, I resolved the issue using the following method. I hope this helps you:
P.S.: I used the official ComfyUI desktop version, but this guide can also be applied to other versions.
1. If you’re unable to install the node, it may be due to a network issue or because a “custom_nude” folder already exists in the Nunchaku custom node directory. If it’s a network issue, you can re-download the files from Git and place them in the “custom_node” folder. Additionally, if “custom_nude” already exists in the Nunchaku custom node directory, you’ll need to delete that folder and reinstall the node using the manager.
2. If you still encounter errors and cannot use the software after installation, it’s because you haven’t installed a file named: nunchaku-1.3.0.devxxxx+cu13.0torch2.10-cp313-cp313-win_amd64.whl
You need to go to the official Nunchaku release page to download the corresponding file:
https://github.com/nunchaku-ai/nunchaku/releases
Please note that your ComfyUI’s Python, PyTorch, and operating system must match the .whl file. For example, in my case:
① Python: 3.13.12 → Identifier: cp313
② PyTorch: 2.10.0+cu130 → labeled cu13.0torch2.10
③ Operating System: Windows 64-bit → Label: win_amd64
If you’re unsure, you can take a screenshot of your version information and ask the AI: “I’m trying to install the nunchaku node. Based on the ComfyUI environment shown in my screenshot, which file should I install?”
After downloading the file, navigate to the directory where the .whl file is stored in the terminal and run:
pip install filename.whl
Or, if you’re using the ComfyUI desktop version like me, find the “Terminal” option and enter the command:
pip install “C:\XXX\nunchaku-1.3.0.dev20260213+cu13.0torch2.10-cp313-cp313-win_amd64.whl”
Remember to replace the path with the location of your .whl file.
Doesn't work. Nunchaku does not install.
Yeah that's an old WF, replace Nunchaku dit loader and nunchaku lora loader with a regular load diffusion model with qwen edit 2511 model and regular lora loader.