Character LoRA of Ellie from The Last of Us Part II, trained on Z‑Image Turbo using Ostris AI‑Toolkit. Focused on realistic in‑game likeness, with 30 captioned images covering multiple outfits, angles, and lighting. Works best for grounded, cinematic shots at 768–1024px.
Best Weight For LoRA: 0.7 - 0.8
Example Prompt including trigger word: "Ellie_TLOU2, a teenage girl with brown hair tied back and green eyes, wearing a green hooded jacket over a dark shirt and carrying a backpack with a flashlight attached, close-up portrait, smiling gently, looking to the side"
Recommended Lora Loader Node: Lora Loader (Z-Image) (CRT) by CRTNodes
Description
Trained on 60 images with more outfits/poses/expressions
Trained for longer at about 3000 steps
FAQ
Comments (7)
👍🏻👍🏻👍🏻
nice can you do ciri or max Caulfield i want to see diffrent art style
YES PLS
Sure, Ciri is definitely on my list. Stay on the lookout for that lora.
Ciri😍
@letekemo583 begging for Max Caulfield aswell
How did you caption the images for the dataset? What tagger produces tags like this?
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.