Meet Asagi Igawa on NoobAI-XL (V-pred / Epsilon), Pony and SD1.5 now!
Note about 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
NoobAI-XL / PonyXL tags:
Igawa Asagi, 1girl, long hair, hair between eyes, black hair, blue hair, green eyes,
Bodysuit: purple bodysuit, bare shoulders, elbow gloves, fishnets, high heel boots,
optional: fishnet legwear
Sweater and pantyhose: orange sweater dress, pantyhose, no shoes
Office lady: white blouse, frills, pencil skirt, black skirt, pantyhose, high heels
Bride: bride, bridal gauntlet, bridal beil, white thighhighs, wedding dress,
Alternatives:
short hair, hair up, folded ponytail - for her formal short hair style.
purple leotard, bare hips, thigh boots - for bare hips bodysuit version
NoobAI-XL quality settings:
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) quality settings (updated):
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):
censored, bad anatomy, deformed, watermark, 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++.
Stable Diffusion 1.5 tags
Main tags:
IgawaAsagi, 1girl, long hair, hair between eyes, black hair, blue hair, green eyes,
Bodysuit: purple bodysuit, bare shoulders, elbow gloves, fishnets, high heel boots
Sweater and pantyhose: orange sweater dress, pantyhose, no shoes
Office lady: white blouse, frills, pencil skirt, pantyhose, high heels
Bride: bride, bridal gauntlet, bridal beil, white thighhighs, wedding dress,
Alternatives:
bare hips, thigh boots - for bare hips bodysuit version
short hair, hair up, folded ponytail - for her formal short hair style.
Description
SDXL-based version
FAQ
Comments (24)
I will use the MODEL and LoRA of the work.
Bro ive been following you for a moment now and i want to say that you got really good taste :)
black lilith power
++ Loras are fkin good
Thank you :3
Please do more! It's so much easier than SD1.5 to create NSFW picture
Nice job on this! It's tagged pretty well. It's making me want to tag my own loras better now.
thank you :3
Thank you for blessing us with another quality hentai lora!
Would you be willing to make Suomi-Sensei from nudist beach ni shuugakuryokou de?
She is hot :3 Maybe :3
@Enigmata seconding for 1.5, suomi and the purple-haired milf from yarimoku beach are hot
there is no quality lora though
How did you manage to draw the Asagi and the orc scene. Last I checked (in my case anyways), Stable Diffusion was unable to draw multiple characters reliably for the most part, much less them interacting with one another. >.<
It is power of PonyXL based models :3
@Enigmata Is that so? Thanks. ^^
Actually, now that I think about it, what prompts did you input to get the orc picture?
@luciuswalker5282 I use 1-2 sentences with little description of interaction between characters. Also I use tags after it.
wow quality is nice .. Please YUKIKAZE !!
Thank you :3 Next Rinko :3
@Enigmata I will wait for yuki :'D
I highly recommend this for making characters in Kagami Hirotaka style using the basic Autism/pony input
hello
i like your work its amazing. but i didn't find Asagi igawa the SD 1.5 Version on tensor.art.
can you put it in?
Hello! It is on site - https://tensor.art/models/702162316340251730
They made many changes on site especially when SD3 was released and they censored everything to hell to get API from stability ai.
That why you couldn't see it. Also they added channels to each lora (if you dont choose your model is not available in main channels) but my old loras were uploaded before these channels were added on site. So I need to choose channel for my SD1.5 loras too. Thank you for reminding about it.
@Enigmata hello when the Asagi SD1.5 will be add to tensor.art ?
@Ocelot_88 hey but it here - https://tensor.art/models/702162316340251730
@Enigmata That’s weird every time i go to it at gives me an empty site.
Sorry to ask but Is there something on my settings I most do an order to see it?
@Ocelot_88 I think the only setting use can fix - enabling mature content in account settings. If you fixed it then it is site bug. I am also wait about 10-20 seconds before page will load. Sometimes script doesn't work at all, lol.
@Ocelot_88 btw I recommend you to try pony or NoobAI-XL versions. Their gives more creativity than 1.5. They also on site.