Please consider supporting me so I can continue to make more Models / LoRA's for the community! --> Buy Me A Coffee
This is a bit of a trash-tier LoRA since there's hardly a useable dataset for Temmie, but it produces interesting results every once in a while, so I thought I'd upload it for anyone who might be interested.
I might take a second crack at making a LoRA for Temmie in the future.
This model was trained using Furry Vixens v2.0
You can use these tags when generating images:
temmie, anthro, cat ears, temmie ears, blue and yellow striped shirt, grey hair, long hair, white fur
And be sure to use these settings!
Steps: 32
Sampler: DPM++ 2M Karras
CFG scale: 7
Size: 384x512
Model: Furry Vixens v2
Denoising strength: 0.6
Clip skip: 2
Hires upscale: 2
Hires upscaler: R-ESRGAN 4x+ Anime6B
Positive Prompt
(temmie:1.2), (chibi:1.2), (cat ears, temmie ears:1.1), paws, (blue and yellow striped shirt), grey hair, long hair, white fur, cardboard box, wooden floor, laying on back, dramatic lighting, (from above, looking at viewer), <lora:Temmie v3:0.7>Negative prompt
(worst quality:1.4), (low quality:1.4), (easynegative:1.2)Description
Initial release.
Trained on Furry Vixens v2.0
FAQ
Comments (4)
The potential is there.
Since there's not that big of a dataset, my main suggestion would be to do your best to generate a variety of good Temmies with this (using inpainting, rerolling the gacha, prompt adjustments etc) - and then take only the best results and feed them back in to make another LoRA. Rinse and repeat.
Yup! That's what I've been doing for all my LoRA's. But since it's already kinda decent it's not a particular priority for this one. Got other things that need making first. 😎💪
you make great models! are you working on anything new atm?
Thank you! Life has been quite busy for me these past few months, but I am slowly working on new version of Furry Vixens.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.