Recommended Prompts

3l3ganc3,realistic,semi-realistic

3l3ganc3, 1girl, semi-realism, long hair, solo, lips

Recommended Negative Prompts

worst quality, bad quality, low quality, lowres, anatomical nonsense, artistic error, bad anatomy, patreon_username, signature, blender, (hooded eyes:1.25)

Recommended Parameters

samplers

DPM++ 2M SDE Karras, DDIM, DPM++ 2M Karras

steps

25 - 30

cfg

4.5 - 7.5

clip skip

2

resolution

832x1240, 512x512

other models

Elegence_Niji-000011 (0899a04d5b), waiNSFWIllustrious_v130.safetensors (a810e710a2), Elegence_Niji-000009 (2e5e9560f2), hassakuXLIllustrious_v21fix.safetensors (847403d47a), 889818.safetensors (3e15ba0038), elegance-000012 (1dbb57c94a), elegance (5031b868de)

Tips

You can brute force it for more dramatic poses.

Works well with several illustrious/SDXL/Pony models, especially for flat anime style and some 3D styles.

Recommended checkpoint combo is Hassaku XL.

Creator Sponsors

Tigger word: 3l3ganc3

Weights : 1 -1.6
This is lora was designed to replicate some the niji 6 realistic anime/draw art style, the data set mostly focused on portraits for male and female but you can brute force it for more dramatic poses.

Some of the features can be triggers using prompts like "3l3ganc3, realistic, semi-realistic" etc..

I have tried it with several illustrious/SDXL/Pony models and it seem to works well flat anime style as well as more 3d styles (though it intended more for the former, I shall update more resources that work with it as I discover them myself).

Give it a shot see what happens :D and thanks for trying our the lora. oh and so far my fave checkpoint combo for this is Hassaku XL

Previous
Ka Marukogedago | Style LoRa - v1.0
Next
DetailedEyes_XL - v3.0

Model Details

Model type

LORA

Base model

Illustrious

Model version

V1

Model hash

141f1ca1d3

Trained words

3l3ganc3

Creator

Discussion

Please log in to leave a comment.