The best girl of Azeroth - Jaina Proudmoore!
Note about NoobAI-XL V-pred update:
Since V-pred model sometimes is oversaturated I recommend to use one of the following extensions (already installed in reForge / Forge):
rescale CFG 0.5 - 0.7 (reForge webui);
Latent Modifier - rescale CFG Phi 0.5 - 0.7 (Forge or reForge webui);
Dynamic Thresholding - mimic cfg 4-5, cfg - 5-6 (Forge or reForge);
APG is now your CFG (reForge, experimental. Better use extensions above).
Also you can install these extensions on A1111 or find these nodes for ComfyUI.
You need latest version of webui which supports zero term snr and V-prediction.
The best model to use V-pred is not pure NoobAI-XL V-pred but Cyberfix!
Character tags:
Jaina Proudmoore, 1girl, mature female,
white hair, blonde hair, streaked hair, single braid, blue eyes, anchor necklace,
Lord Admiral outfit:
single pauldron, cape, cropped jacket, corset, detached sleeves, gloves, blue pants, long skirt, single gauntlet, knee boots, cleavage
Optional features:
holding staff
anchor piercing, nipple piercing
For interactions:
orc, zandalari troll, troll /(warcraft/);
night elf /(warcraft/), Tyrande Whisperwind;
dark elf, Sylvanas windrunner;
tauren, worgen, furry with non-furry;
Put "masterpiece, best quality, good quality" in positive and put "low quality, worst quality" in negative.
Use cfg 4-5. Don't use higher CFG!
If you have over-constrasted picture and cfg 4-5 didn't help you can try to put in negative "colorful".
FOR V-PRED:
Put "masterpiece, good quality, best quality, very awa, very as2" in positive and put "worst aestetic, low quality, worst quality" in negative
Style settings (very important):
score_9, score_8_up, score_7_up, score_6_up, score_5_up, source_anime
You can remain only "score_9" if you use style lora because all scores except score_9 supress style loras.
Negative prompt (recommended):
lowres, censored, mosaic censoring, bar censor, blurry, bloom, bad anatomy, deformed, head out of frame, watermark, worst quality, low quality, jpeg artifacts
3D if you don't want 3D.
Preview images can help.
LoRA was trained on Animefull due to best compitability with all anime / 2.5D checkpoint models.
0.85 - 1 strength of Lora is the best radius (For combining with other LoRAs, I recommend reducing weight. If you don't combine with another LoRA you can use 1.0 because it is not overfitted).
Some necessary tokens for better experience:
Main tokens:
JainaProudmoore, 1girl, solo, holding glowing staff, magic,
white hair, blonde hair, streaked hair, single braid, eyeshadow, lipstick, makeup, detailed face, blue eyes, anchor necklace,
Lord Admiral outfit:
single pauldron, cape, cropped jacket, corset, detached sleeves, gloves, (blue pants:1.1), (skirt:1.1), single gauntlet, knee boots
Also you can use another tokens for clothes and appearance as you can see in my preview.
I will be glad to receive feedback from you and a demonstration of your art with my LoRA!
Don't forget to like LoRA model :3
NOOB-AI XL V-PREDICTION TYPE MODEL! PLEASE READ NOTE ABOUT V-PRED BEFORE USE!
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.