Tutu/Ballet outfit - LoHa版本v1.20 (ID: 33087)

Tutu/Ballet outfit - LoHa版本v1.20 (ID: 33087)

Please check out my Ko-Fi page if you are interested in supporting me.

LoRA commissions open! -> Fiverr

This is a LoHa LoRA! You need the extension! Why? They do a lot better with multi-concepts.

This is retrained from thesauceer dataset, just a version of his Tutu LoRA, please check out his original work! He was kind enough to share his dataset.

Trigger words for V3.20:

positive: <lora:Tutuv320:0.5>(tutu)

You can also try WITH VERSION V2.20: "ribbon-trimmed skirt", "layered skirt" and "miniskirt".
If failing to make full shirt, try adding either "leotard" or "tank top" or "covered navel" to prompt.

Keep in mind you might have to adjust LoRA and/or tag weight for it to appear, defaults to "ribbon-trimmed skirt" most of the time! Dataset wasn't an exactly split between the different concepts.

Follow the steps in the Model Version notes to reproduce my images.

Sample images generated with Hassaku.

All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.

It was trained on 45 512x512 images provided by thesauceer, 20 epochs using Animefull-final-pruned for the Training Model.

Danbooru tags generated by Waifu Diffusion 1.4 Tagger.

描述:

Generate using a weight of 0.5-1.0 like this: <lora:Tutuv120:1>.

How I archived my generations:

  1. txt2img: DPM++ SDE Karras with 20 steps, 512x512(can go up to 768 for wide or tall), Restore faces on (using CodeFormer weight 1.0 in Settings), Hires-fix on, to 1024x1024 (double original size) with your preferred upscaler and Denoise 0.4, CFG 7. Then send to img2img!

  2. img2img: DPM++ SED Karras with 20 steps, Restore faces on (CodeFormer weight 1), rescale to 1536x1536, CFG 7, Denoise between 0.3-0.7 (based on how much you want to improve the image), SAME PROMPT! Send to extras when happy with img2img/inpaint results.

  3. extras: Scale to x3 (final will be 4608x4608, I suggest going lower, I did x3 just for the samples here) Upscaler 1 - FatalAnime 4x, Upscaler 2 - SwinIR 4x with 0.10 visibility, GFPGAN 0.10 visibility, CodeFormer 0.10 visibility.

If anyone is curious about my version names: v{version}.{trainingEpochs}

训练词语: tutu,ribbon-trimmed tutu

名称: Tutu.safetensors

大小 (KB): 22872

类型: Model

Pickle 扫描结果: Success

Pickle 扫描信息: No Pickle imports

病毒扫描结果: Success

Tutu/Ballet outfit - LoHa

Tutu/Ballet outfit - LoHa

Tutu/Ballet outfit - LoHa

Tutu/Ballet outfit - LoHa

Tutu/Ballet outfit - LoHa

资源下载
下载价格VIP专享
仅限VIP下载升级VIP
犹豫不决让我们错失一次又一次机会!!!
原文链接:https://1111down.com/896974.html,转载请注明出处
由于网站升级,部分用户密码全部设置为111111,登入后自己修改, 并且VIP等级提升一级(包月提升至包季,包季提升到包年 包年提升至永久)
没有账号?注册  忘记密码?

社交账号快速登录