Last character from Shion - Lydia is on NAI / IL /PonyXL / SD1.5 animefull now!
NAI / IL / Pony tags:
Lydia, 1girl,
short hair, blue hair, green eyes,
Outfit:
highleg leotard, white leotard, thigh boots, elbow gloves,
Optional:
holding sword, katana, torn leotard, covered nipples, cameltoe
SD1.5 tags:
Main tokens:
Lydia, 1girl,
blue hair, short hair, green eyes,
bodysuit, highleg, gloves, thigh boots
NoobAI-XL quality prompt:
Put "masterpiece, best quality, good quality" in positive and put "low quality, worst quality" in negative.
Use euler, cfg 4-6. 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 NoobAI-XL V-pred:
Check my guide about V-pred image generating!
The best model to use V-pred is Cyberfix! But pure NoobAI-XL V-pred is also good.
For Illustrious mixes and NoobAI-XL Epsilon: use NoobAI-Xl Epsilon (especially mixes based on NoobAI-XL Epsilon!).
Guide about NoobAI-XL Epsilon
PonyDiffusion v6 (XL) quality settings:
Style settings for PonyXL (important):
score_9, score_8_up, score_7_up, score_6_up, uncensored, BREAK
Negative prompt for PonyXL (recommended):
dutch angle, censored, watermark, jpeg artifacts, muscular female
SD1.5 quality settings:
masterpiece, high quality
in negative: (worst quality, low quality:1.2)
Hires fix and adetailer settings (for 1.5 and Pony)
Hires.fix: Upscaler foolhardy_remacri (download and put in "ESRGAN" folder in "models" if you are using automatic1111 or forge).
Hires steps: 16-18
Denoising strength: 0.3
Adetailer: denoising strength 0.3. Detection model confident threshhold: 0.7-0.8.
Best sampling method is euler a, 25-40 sampling steps. You don't need any DPM++.
I will be glad to receive feedback from you and a demonstration of your art with my LoRA!
Description
FAQ
Comments (7)
Another one on my To Do list that you nailed, your hitting it out of the park! Thank you!
May I ask what model did you use to train these characters? They seem extremely well trained and very versatile using them on different models.
Would love to see the training data you used. But I totally understand not sharing those. Just saying because i've been trying to do similar characters from other OVAs but the scenes include so many varied concepts that finding a decent model that can understand the concepts is not easy and tend to not learn the subject structurally well.
Hi! Thank you. Model for training - animefull (also known as NAI and model.ckpt). You can find it on hugging face.
@Enigmata Wow interesting! Didn't think to use NAI model to train, i'll give that a go for my next model im training! Thanks!
Please make a pony version
I am planning to port all my 1.5 loras to pony but it takes time :3
made!
@Enigmata THANKS