Type | |
Stats | 585 1,951 24 |
Reviews | (118) |
Published | Nov 11, 2023 |
Base Model | |
Training | Steps: 1,999 Epochs: 10 |
Usage Tips | Clip Skip: 2 Strength: 0.8 |
Trigger Words | AltSiaV4 |
Hash | AutoV2 464BE68CC3 |
N°51 Release, アルテマティア - Artemasia/Ultimatia from Ragna Crimson - ラグナクリムゾン.
Put everything in Filter for seeing all images!
Click on Show more for Weight & Trigger recommendation, Also click on About This Version at Right Corner for more Info.
The Dragon Queen - I wanted to Create a Lora's on her, It's somewhat early, tho i did get a good Datasets for her, ALL Original Art & Anime ScreenCaps were Upscaled With x4-AnimeSharp Upscaler & Some Edited, Very time consuming Ahah.
Good Quality & Many Differents Angles (Full Body/UpperBody, From Above, Below, Behind, Side), with a Not Bad Flexibility. (Will Update when S1 is finished + More Original Art).
About this Lora:
This Lora is trained on 132+ Images at the Max Quality Possible, (Majority Of AnimeScrencCaps 1080P Quality + Official Art/Original Art in 4K Quality), I sorted everything manually, Only picked the best possible. (SFW+) - All Artwork used in Datasets are Upscaled & All Updated).
I Removed all the textmark from Datasets + Upscaled some Artwork with x4-AnimeSharp for a Better Output Quality + Some Artwork & Screencaps, I edited them for a better Output Quality.
NAI Used, Work with Majority of the Anime Model's.
Flexibility is Not Bad/Good. (See Examples Images). - (0.6-0.8 Weight).
Good Precision on Official Default Skin & Can do Also Other Clothes that don't exist. (Only Downside = Bracelet ''Sometime'' appears on both arms, but generally you get it Right).
Can do Original Art & AnimeTV Like.
Increased size 74Mb + (With Optimal Settings), Like this Multicolored Eyes & Wings are a little more Consistent + Precise.
Work with other Lora like Add Detail & Other. (+ ADetailer i recommend).
Probably Can do in Realistic Cosplay, Not 100% Sure.
About Trigger Words & Prompts: AltSiaV4 (For Trigger) & for prompts just refer to examples image.
Weight recommended: 0.6-1. - Work perfectly at Weight 1, Best result: 0.8-1
Negative Embedding used: EasyNegative, BadPrompt2 and sometime negative_hand-neg.
Leave a Review & Share you're image in comments if you appreciate this Work :)