Sign In

Zummi Gummi - ILXL (Adventures of the Gummi Bears)

18

58

182

9

Verified:

SafeTensor

Type

LoRA

Stats

58

182

130

Reviews

Published

May 3, 2025

Base Model

Illustrious

Usage Tips

Clip Skip: 2
Strength: 1

Trigger Words

zummigummixl, anthro, bear, glasses, pince-nez, hat with feather, blue tunic, red cape, gold medallion

Hash

AutoV2
E83F43E1C7

Main prompt tags: zummigummixl, anthro, bear, glasses, pince-nez, hat with feather, blue tunic, red cape, gold medallion <----------- should always be included

Style control:

  • for the retro TV show style add following positive prompts: cartoon, toony, retro

  • to avoid the retro cartoon style put cartoon, toony, retro into negative prompt

  • for mixed style only put cartoon into positive prompt


Recommended samplers:
Euler Ancestral Scheduler: Normal CFG: 6.0 Steps: 20 Lora strength: 1.0
DPM++ 2M SDE Scheduler: Karras CFG: 6.0-7.0 Steps: 20-25 Lora strength: 1.0
euler_ancestral_cfg_pp Scheduler: Normal CFG: 1.0 Steps: 20-25 Lora strength: 1.0

Prompt tips (green - positive, red - negative:
- purple bear if his fur changes to brown
- glasses, pince-nez, blue tunic, red cape, hat with feather, gold medallion, sash - full clothing
- hat, glasses, pince-nez into negatives to remove the hat/glasses (or just remove from positives)
- black eyes will help reinforce cartoon style since Illustrious likes giving him detailed purple eyes
- wrinkles, mature if you want Zummi to appear older (but still canon)
- 4 fingers can help to get the canonical version of Gummi hands
- (pince-nez:1.1) in case you need to reinforce his glasses
- golden medallion with g helps with his Gummi medallion depiction - Illustrious does not like his medallion - it will often look too detailed or change letters, becomes worse with higher CFG/steps. No easy fix unfortunately

The LoRa should support all kinds of Illustrious checkpoints. Tested working well with the following:

  • Nova Furry XL v5.0

  • WAI-NSFW-illustrious-SDXL v12.0

To improve details:
- generate using higher base resolution (e.g. 1216x1216) or use latent upscaling / highres fix - especially when trying to do full body poses
- for fixing wonky face/eyes I use FaceDetailer node (comfyui) + Adetailer Face finder model


Last image in the gallery can be imported into ComfyUI with a basic workflow:


Just Copy&Paste into ComfyUI (you might be required to download missing nodes)