Sign In

[IL] Diana Lombard (Martin Mystery)

95

Download

1 variant available

SafeTensor

217.88 MB

Verified:

Type
LoRA
Stats

70

95

31

Reviews
Published

Aug 26, 2026

Base Model

Illustrious

Training
Steps: 777
Epochs: 15
Usage Tips
Clip Skip: 1
Hash
AutoV2
68E087E1C1
Trigger Words
D_L_M_M, brown hair, long hair, hairclip
shirt, raglan sleeves, capri pants, sneakers
default creator card background decoration
Uploads - 520

520

Followers - 4538

4.5K

Likes - 13533

13.5K

Silver Writer Badge

Created on Civitai

2222166e-0536-4755-910a-fb4da42c8e54.png

Martin’s bookish, jumpy, easily grossed out, unathletic, skeptical of supernatural (despite having encountered it dozens of times) step-sister from the Martin Mystery cartoon. Previous Illustrious LoRAs were trained on pictures of the 4:3 series stretched to 16:9 (courtesy of the original official YouTube upload) or were weak on inherent style, so I tried to made one using proper 4:3 data.

Click here to see 70+ LoRAs otherwise hidden from my profile at the whims of credit card companies. You can help support making models like this by posting stuff you've made with it to the gallery using the "add post" button, that helps me earn back the training cost at no cost to you.

Tags: D_L_M_M, brown hair, long hair, hairclip
Negative: multiple hairclips (improves, but doesn't fix, triple hairclip problem)
Main outfit: shirt, raglan sleeves, capri pants, sneakers
Accessory: shoulder strap, shoulder bag (use only first if only the strap is visible)
CIHL Operative: helmet, two-tone bodysuit, high heel bodysuit,
Date dress: ponytail, hair bobbles, hoop earrings, pink lipgloss, single-shoulder dress, detatched sleeves, striped socks,
Pajamas: t-shirt, cat print, pajama shorts,

V1 was made with 1 official art of her in main outfit, 29 screenshots of her in her main outfit, 13 of her in the CIHL suit, and 11 of various other outfits. V1.2 was made after testing initial training of 1.0 (not published here, can if someone really wants it) revealed the hairclip was really weak: Both getting the number wrong, and making the whole section blurry. Led to adding 15 new images and a change in tag (from multiple hairclips) to try to get it better, as well as removing the tag from some long shots it’s technically visible in. It's certainly an improvement, though still a flaw.