Sign In

Tummi Gummi - ILXL (Adventures of the Gummi Bears)

1.8k

Download

1 variant available

SafeTensor

217.88 MB

Verified:

Type

LoRA

Stats

96

1.8K

765

Reviews

Published

May 3, 2025

Base Model

Illustrious

Hash

AutoV2
66094083FF

Trigger Words

tummigummixl, anthro, male focus, blue bear, brown tunic, red cap with feather

Main prompt tags: tummigummixl, anthro, solo, male focus, blue bear, brown tunic, red cap with feather, shoulder bag <------ 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:
- DPM++ 2M SDE Scheduler: Karras CFG: 6.0-7.0 Steps: 20-25 Lora strength: 1.0
- Euler Ancestral Scheduler: Normal CFG: 6.0 Steps: 20 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):
- blue bear because Illustrious will turn him brown too often
- fat if Tummi is not generated plump enough
- brown tunic, red cap with feather, shoulder bag, sash, sandals - full base clothing (sandals will force full body shots)
- white cap, white pajamas (instead of brown tunic) - pajama version
- red cap with feather into negative positives to remove his hat
- black eyes will help reinforce cartoon style (Illustrious likes giving him detailed colored eyes)
- 4 fingers should help to get the canonical version of Gummi hands
- shoulder bag in negatives if his shoulder strap appears duplicate or appear even if you didn't prompt for it
- vhs filter will give the style even more retro feel closer to the original cartoon

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)