VNCCS - Visual Novel Character Creation Suite
VNCCS is NOT just another workflow for creating consistent characters, it is a complete pipeline for creating sprites for any purpose. It allows you to create unique characters with a consistent appearance across all images, organise them, manage emotions, clothing, poses, and conduct a full cycle of work with characters.
Many people want to use neural networks to create graphics, but making a unique character that looks the same in every image is much harder than generating a single picture. With VNCCS, it's as simple as pressing a button (just 4 times).
Character Creation Stages
The character creation process is divided into 5 stages:
1. Create a base character
2. Clone any existing character
3. Create clothing sets
4. Create emotion sets
5. Generate finished sprites
6. Create a dataset for LoRA training (optional)
---
If you find my project useful, please consider supporting it! I work on it completely on my own, and your support will allow me to continue maintaining it and adding even more cool features!
Installation
Find VNCCS - Visual Novel Character Creation Suite in Custom Nodes Manager or install it manually:
1. Place the downloaded folder into ComfyUI/custom_nodes/
2. Launch ComfyUI and open Comfy Manager
3. Click "Install missing custom nodes"
4. Alternatively, in the console: go to ComfyUI/custom_nodes/ and run git clone https://github.com/AHEKOT/ComfyUI_VNCCS.git
Required Models
VNCCS requires the following models in ComfyUI. Make sure they are installed in the correct directories:
Stable Diffusion Checkpoints models/checkpoints/)
- Any illustrious based model.
- Should work on any SDXL model, but not tested.
LoRA Models models/loras/)
- vn_character_sheet_v4.safetensors
- DMD2/dmd2_sdxl_4step_lora_fp16.safetensors
- vn_character_sheet.safetensors
- IL/mimimeter.safetensors
- QWEN/all_loras_from_here
ControlNet Models models/controlnet/)
- SDXL/AnytestV4.safetensors
- SDXL/IllustriousXL_openpose.safetensors
Face Detection Models models/ultralytics/bbox/ and models/ultralytics/segm/)
- bbox/face_yolov8m.pt
- bbox/face_yolov9c.pt
- segm/face_yolov8m-seg_60.pt
SAM Models models/sams/)
- sam_vit_b_01ec64.pth
Upscale Models models/upscale_models/)
- 4x_APISR_GRL_GAN_generator.pth
- 2x_APISR_RRDB_GAN_generator.pth
All models must be placed in the standard ComfyUI directories according to their type.
You can download them from my huggingface: https://huggingface.co/MIUProject/VNCCS/tree/main