Recommended Prompts

(kuroduki (pieat)),(alzi xiaomi:1.1),(rei (sanbonzakura):1.1),(koujuan:1.1),nose,lips,(chromatic aberration:1.1),(colored inner hair), eyeshadow,(shiny),(shiny hair), multicolored hair,glowing eyes

(xilmo:1.3,)(nj (imai):1.2),(wenjun lin:0.9) (nj (aoai):1.1)

(wanke:1.2),(mon (monmon2133):0.9),(mochizuki kei:0.95), (tira 27:0.7)

(akizero1510:1.25),(am314:1.15),(agoto:1.05),((bai qi-qsr:0.9)

(tianliang duohe fangdongye:1.35), (asagina gi:1.55),(kaneni:0.9),(zukky:0.75),((jazz jack:1.2)), (nep:0.9),(urakata (uracata):0.75),(tira 27:1.2),chibi

(alzi xiaomI:1.3),(mogumo:1.2),(fukuro daizi:1.2),(starshadowmagician)

(esuthio:1.2), (k-suwabe:1.2),(nj (aicd):1.4),(john kafka:0.9)

best quality, masterpiece, absurdres, newest, 1girl, solo, looking at viewer

Recommended Negative Prompts

worst quality, bad quality, jpeg artifacts, (bad hands, bad finger, anatomy), (artist name, copyright name, watermark, text, english text:1.2), (bad feet, bad toes)

Recommended Parameters

samplers

DPM++ 2M SDE

steps

20

cfg

4 - 6

clip skip

2

resolution

1192x968, 872x1240, 2016x1516, 1200x880, 1208x784, 840x1184, 896x1224, 984x1296, 848x1240

other models

GENESIS_MK0.4 (3b4fb56f8406), illustriousXL_v01 (3e15ba0038)

Recommended Hires (High-Resolution) Parameters

upscaler

R-ESRGAN 4x+, R-ESRGAN 4x+ Anime6B

upscale

1.7

steps

20

denoising strength

0.5 - 0.52

Tips

Experiment with different combinations of over 200 trigger words to achieve various art styles.

Use recommended sampling method DPM++ 2M SDE with SGM Uniform schedule type.

CFG scale is recommended between 4 and 6.

Refer to Art Style, Nji Style, Lighting Effect, and Character Tag Lists via provided Huggingface links for building prompts.

Creator Sponsors

If you enjoy using this LoRA model, consider supporting my work through Ko-fi to help upgrade my hardware capabilities.

If you'd like me to develop a personalized LoRA model tailored to your needs, check out my custom service offerings on Fiverr!

If you enjoy using this LoRA model, consider supporting my work through Ko-fi to help upgrade my hardware capabilities.

If you'd like me to develop a personalized LoRA model tailored to your needs, check out my custom service offerings on Fiverr!

GENESIS is a LoKr model based on illustriousXL_v01 and trained with over 17000 images. It utilizes Danbooru tags and natural language for labeling and includes over 200 trigger words. When using GENESIS, it is recommended to experiment with different combinations of trigger words to achieve various art styles.

GENESIS 是基于 illustriousXL_v01为底模,并使用 17000 多张图片进行训练而成的 lokr,同时使用了danbooru tags和natural language进行打标并设定了超过 200 个触发词。在运用 GENESIS 时建议通过对不同触发词的排列组合,以获取不同的画风。

Here are some combinations I use, feel free to try them out:

下面是几个我在使用的几个组合,欢迎各位尝试:

- (kuroduki (pieat)),(alzi xiaomi:1.1),(rei (sanbonzakura):1.1),(koujuan:1.1),nose,lips, (chromatic aberration:1.1),(colored inner hair), eyeshadow,(shiny),(shiny hair), multicolored hair,glowing eyes,

- (xilmo:1.3,)(nj (imai):1.2),(wenjun lin:0.9) (nj (aoai):1.1),

- (wanke:1.2),(mon (monmon2133):0.9),(mochizuki kei:0.95), (tira 27:0.7),

- (akizero1510:1.25),(am314:1.15),(agoto:1.05),((bai qi-qsr:0.9),

- (tianliang duohe fangdongye:1.35),, (asagina gi:1.55),(kaneni:0.9),,

(zukky:0.75),((jazz jack:1.2)), (nep:0.9),(urakata (uracata):0.75),(tira 27:1.2),chibi,

- (alzi xiaomI:1.3),(mogumo:1.2),(fukuro daizi:1.2),(starshadowmagician),

- (esuthio:1.2), (k-suwabe:1.2),(nj (aicd):1.4),(john kafka:0.9),

Recommended Settings:

Sampling Method: DPM++ 2M SDE

Schedule Type: SGM Uniform

CFG Scale: 6-4

recommended weight: 0.9-0.6

建议设置:

采样方法:DPM++ 2M SDE

Schedule type:SGM Uniform

CFG Scale:6-4

推荐权重: 0.9-0.6

Art Style Tag List:

- https://huggingface.co/rim0/GENESIS/blob/main/Art%20StyleV2.txt

Nji Style Tag List:

- https://huggingface.co/rim0/GENESIS/blob/main/Nji%20StyleV2.txt

Lighting Effect Tag List:

- https://huggingface.co/rim0/GENESIS/blob/main/Lighting%20Effect.txt

Character Tag List:

- https://huggingface.co/rim0/GENESIS/blob/main/CharacterV2.txt

Contributor

Previous
epiCPhotoXL LoRA - v1.0
Next
Taru | Fictional Girl | Illustrious - Taru V1

Model Details

Model type

LoCon

Base model

Illustrious

Model version

v0.4

Model hash

5c56b73d67

Creator

Discussion

Please log in to leave a comment.