This LoRA brings Manmayer Gunko from One Piece into SDXL. I wanted to capture her highly unique and distinctive appearance—including her striking heterochromia, bandages, and signature outfit—while keeping the model flexible enough for a wide variety of generations.
📢 Note on Dataset: Since she currently has very few shots/limited screen time, the dataset is small. I will be updating and refining this model as soon as the next episodes drop and more source material becomes available!
⚙️ Technical Details
Base Model: Trained on
waiIllustriousSDXLand designed primarily for Illustrious-based checkpoints. Results may vary on other SDXL models.Dataset: Trained on a curated dataset of high-quality images to accurately capture her authentic design and distinct features.
Recommended Weight: 0.8–1.0 (Start at 1.0 and adjust depending on your checkpoint and prompting style.)
🎨 How to Use
Core Trigger Words:
1girl, Gunk0, short hair, blue hair, Heterochromia, blue eyes, red eyes, mouth covered in bandages
Recommended Outfit Tags:
cap, black long sleeve dress, black panties, pink cape
Example Prompt:
Anime art, 1girl, Gunk0, short hair, blue hair, Heterochromia, blue eyes, red eyes, mouth covered in bandages, cap, black long sleeve dress, pink cape, standing, front view, looking at viewer, masterpiece, high quality
For best results, keep the core character and facial tags in your prompt, especially when experimenting with different outfits, poses, or environments.
📸 Sample Prompt Ideas
Casual portraits focusing on her unique heterochromia and bandages
Full body character shots showing off the dress and cape
Action and adventure scenes in typical One Piece style environments
Alternative outfits or modern streetwear mixes
Dramatic lighting to emphasize her mysterious look
The LoRA was trained to capture Gunko's striking appearance while remaining flexible enough for different poses, backgrounds, and creative variations.
📬 Requests & Feedback
Feel free to post your generations in the review section. I always enjoy seeing what people create, and it helps me evaluate how the LoRA performs across different checkpoints and prompt styles.
If there is a character you'd like to see trained next, leave a comment and I'll consider it for a future release.
If you find this LoRA useful, please leave a rating and share your results. It helps others discover the model and supports future uploads.
❤️ Support My Work
If you enjoy my releases and want to support future models, you can check out my Patreon:
Even a follow, rating, or shared generation helps a lot and keeps future projects going.
Thank you for downloading, and have fun creating with Manmayer Gunko!








