Type | |
Stats | 316 566 |
Reviews | (85) |
Published | Apr 19, 2024 |
Base Model | |
Training | Steps: 20,000 Epochs: 10 |
Usage Tips | Clip Skip: 2 |
Trigger Words | twyk,1girl,solo,large breasts, collarbone, bare shoulders, lipstick, makeup,turtleneck ,impossible leotard, highleg leotard, purple leotard, impossible clothes, see-through, shiny clothes, skin tight, fingerless gloves, elbow gloves, thigh boots, high heel boots, twyk,1girl,solo,large breasts,lipstick, makeup,collarbone,black choker, white blouse,long skirt, skirt,side slit,pantyhose,high heels, Brush tentacles,tentacles, tentacle sex, eldritch abomination,too many warts, bumpy, lumpy, wormy, slime (substance), |
Hash | AutoV2 720171CC09 |
-This is my 11th XL Chara Lora -
Base model : Genimagine XL(for LoRA training)
Recommend a weight : 0.85 ~ 1
Recommend Models : Genimagine XL(for LoRA training),Animagine XL V3.1
Recommend Prompts (Chara) : twyk,1girl,solo,large breasts, collarbone, bare shoulders, lipstick, makeup,
Recommend Prompts (clothing_1): turtleneck ,impossible leotard, highleg leotard, purple leotard, impossible clothes, see-through, shiny clothes, skin tight, fingerless gloves, elbow gloves, thigh boots, high heel boots,
Recommend Prompts (clothing_2):black choker, white blouse,long skirt, skirt,side slit,pantyhose,high heels,
Recommend Prompts (tentacles) : Brush tentacles ,tentacles, tentacle sex, eldritch abomination, lumpy , bumpy, warts,
Recommend Prompts (Penis) : spiked penis ,
(Try different things if necessary.)
※Since the tag "twyk" aggregates tag elements such as hair style, hair color, etc, you probably do not need to bother setting it.
If it is less effective, try adding an optional prompt.
-Review(for personal reflection)-
I tried to create Lora using the checkpoints created by Mr.RedRay.
It may be able to output the original taste of the checkpoints without reproducing too much of the original training data set.
Another thought is that the shape of the tentacles, etc. may be fearlessly broken due to over-processing of the original training data set.
As far as generating a normal picture, there should be no problem.
I intend to re-bake it again using Animagine 3.1 checkpoints.
-Dear AnimagineXL model author-
Compared to the previous version, this version seems to be more stable.
I really like the background depiction of the models you create.
I would be very happy if you continue to create good models.
Don't take it too hard! Let's take it easy!
Note : This is an experimental Lora to check its versatility, I may create a new version to increase its versatility.(Mainly about learning materials and tags)
I would like to see the work of everyone using this Lora, whether normal or NSFW, so please post a variety!
-Dear Affluent People Who Can Afford It-
The electricity bill is so terrible that I will weep and rejoice if you could grace me with a cup of coffee!