FOR PERSONAL USE ONLY. WILL BE DELETED IF REQUESTED.
>Tips via Ko-fi or Civitai Buzz are appreciated. (Feel free to DM me LoRa suggestions)
>Find more characters who are taken or crushing at collection [RG4535] IN LOVE
Recommended Appearance/Outfit
CLASSIC
(anime coloring:1.1),
da7kanoko, small breasts, brown hair, purple eyes, swept bangs, long hair, low ponytail, side ponytail, hair over shoulder, flower earrings,
red dress, strapless dress, frilled dress, long dress, white cardigan, open cardigan, sleeves past elbows,
brown footwear, strappy heels, sandals,
FESTIVAL
(anime coloring:1.1),
da7kanoko, small breasts, brown hair, purple eyes, swept bangs, short hair, hair up, single hair bun, hair flower, pink flower, asymmetrical bangs, hair behind ear, hair stick, earrings, green kimono, vertical-striped kimono, animal print kimono, yellow sash,
BIKINI
(anime coloring:1.1),
da7kanoko, small breasts, brown hair, purple eyes, swept bangs, short hair, hair up, folded ponytail, stud earrings,
frilled bikini, pink bikini, front-tie bikini top, side-tie bikini bottom,
BRAIDED BUN (HAIRSTYLE)
(anime coloring:1.1),
da7kanoko, small breasts, brown hair, purple eyes, swept bangs, short hair, hair up, single side bun, braided bun, french braid, pearl earrings,
SHORT HAIR (HAIRSTYLE)
(anime coloring:1.1),
da7kanoko, brown hair, purple eyes, swept bangs, short hair, bob cut, wavy hair,
A LoRA strength of 1.0 ensures maximum outfit accuracy but impacts the overall art style (character features remain intact). Adjust the weight as needed. (The sample is .9)
Setting
Checkpoint: WAI-illustrious-SDXL v16
Sampler name: euler a | Scheduler: normal | Cfg: 1.2 | Steps: ~12
HighRes-Fix: 4xUltrasharp | x1.25 | Steps: 12 | Denoise: 0.35 | Iterations: 1~2 (Optional, Depends on your composition)
(If you're not using Noob Hyper Dmd, just use a general metrics for generation)
DISCLAIMER:
THIS LORA MODEL IS CREATED SOLELY FOR ACADEMIC RESEARCH AND PERSONAL USE. IT IS STRICTLY PROHIBITED TO USE IT FOR COMMERCIAL PURPOSES OR PROFIT. ADDITIONALLY, IT MUST NOT BE USED TO GENERATE NSFW CONTENT. ANY CONSEQUENCES ARISING FROM VIOLATIONS OF THESE TERMS SHALL BE THE SOLE RESPONSIBILITY OF THE USER
Description
FAQ
Comments (11)
Excuse me, is there anything Lora didn't mention? Because the image I generated is completely different from the one you sent
Hi yantongxin59383,
I just downloaded it and tried it with a new and clean workflow and everything looks good to me. You can check the screenshot of my workflow here: https://lurl.cc/4iOhY
*I only use Lora: Noob Hyper Dmd in this workflow
I suggest you try it on a new and clean workflow again, feel free to DM the screenshot if the result is still bad :)
@RG4535 谢谢您的回复。我已经看到了您的工作流程图，但我更喜欢您在网站上展示的艺术风格。请问您是否添加了某种LoRA？
@yantongxin59383 Yes, please check the description. I used a self trained Lora for this :)
@RG4535 May I ask if it is a Lora named T85P55? I have also added that Lora, but it still cannot achieve the effect of your display image, similar to the workflow image in your comment
@RG4535 这与我使用Webui有关吗，因为我不会使用工作流程
@yantongxin59383 I don't think so, (though I haven't used webui for a long time), but I'm sure you can also apply one character LoRa and one artstyle LoRa at the same time... Are you using WAI-illustrious-SDXL v16?
@RG4535Yes, I am using WAI illustrious SDXL v16, and Lora is the same as yours. Other parameters are also set according to the settings you posted. It can only generate the appearance in your comment section link and cannot generate the appearance on the website. I really like the display images on the website
@yantongxin59383 Hi, unfortunately, I can't replicate the style in the sample either :(
It was generated in a quite messy workflow and the result might be affected by some clothes or lighting LoRa inside the workflow. I'll let you know if I found out how I did that in the future. For now, I suggest you adjust the "Noob" weight as "1" (the hyper lora I mentioned in the description) and remove the "anime coloring" in the prompt, "might" get a result that slightly close to your expectation.
@RG4535 感谢您的耐心回答