Trigger Word: d4p4n
Recommended Settings:
LoRA Weight: 0.8 – 1.0 (start at 0.9)
Sampling Method: Euler a or DPM++ 2M Karras
Steps: 25–30
CFG Scale: 5.0 – 7.0
Prompting Tips:
To get his iconic look, use the following tags in your prompt:
d4p4n, solo, 1boy, furry male, panda, giant panda, fat, round belly, white fur, black fur, round ears, bottomless, black paws, clawsFor his Outfit:
black leather jacket, white tank top, graphic print, blue sunglasses, reflective sunglassesKnown Issues / Tips:
The LoRA is trained with a focus on "fat/belly" – if he looks too thin, increase the weight of the fat and belly tags.
For the greatsword, adding holding sword, greatsword helps with consistency.
This LoRA has sometimes some issues generating correctly the wok on his back "(wok, wok on back)" and the items on his belt "(white cloth, silver bottle, item on belt)"
Author's Note / Feedback
This is my very first LoRA model, and I'm still learning the ropes of training with Illustrious! I'm quite happy with how Da Pan turned out, but I'd love to hear your thoughts.
If you encounter any issues or have suggestions for improvement, please let me know in the comments!
I’d be thrilled to see what you create with him. Please consider uploading your generations to the gallery!
Note: This is a fan-made model. Please do not use it for commercial purposes.