Type | |
Stats | 428 151 19 |
Reviews | (69) |
Published | Jun 19, 2024 |
Base Model | |
Training | Steps: 5,000 Epochs: 22 |
Usage Tips | Clip Skip: 2 Strength: 1 |
Trigger Words | Beatrice Kushan, mature female, 1girl, long hair, purple eyes, lipstick, lips, mole under eye military uniform, brown pants, thigh boots, white gloves, white coat, coat on shoulders, white lingerie, white thighhighs, white bra, garter belt, garter straps |
Hash | AutoV2 D07470EB6B |
,__mature female, dark-skinned female, solo,.jpeg)
Beatrice Kushan from Kangoku Senkan 3 is on Pony, NoobAI-XL (Illustrious) and SD1.5 now!
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.
PonyXL / NoobAI-XL and SD 1.5 tags:
Main:
Beatrice Kushan, mature female, 1girl,
long hair, purple eyes, lipstick, lips, mole under eye
Military uniform:
military uniform, brown pants, thigh boots, white gloves, white coat, coat on shoulders,
White lingerie:
white lingerie, white thighhighs, white bra, garter belt, garter straps
NoobAI-XL quality prompt:
Put "masterpiece, best quality, good quality" in positive and put "low quality, worst quality" in negative.
Use euler, 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".
PonyDiffusion v6 (XL) settings:
Style settings (very important):
score_9, score_8_up, score_7_up, score_6_up, score_5_up,
Negative prompt (recommended):
dutch angle, censored, mosaic censoring, jpeg artifacts, muscular
Upscaler / adetailer settings:
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 / euler a, 25-40 sampling steps, You don't need any DPM++
Don't forget to like LoRA model :3