TerribleAnimal Artist Style - [Illustrious]

详情

模型描述

Artist Style LoRA – TerribleAnimal

Artist: TerribleAnimal
LoRA Type: Artist Style
Trigger Word:
t3rribl3anim4l
Recommended Weight: 0.9–1.1 (ideal around 1.0)
Base Model: Illustrious v1.1


Overview

This LoRA is designed to capture the signature artistic look of TerribleAnimal—a style defined by moody desaturated palettes, razor-thin precision linework, and clean, flat cel-shading with a distinct noir atmosphere.


Training Information

  • Steps / Epochs: 3000 steps across 38 epochs

  • Clip Skip: 2

  • Dataset Size: 50

  • Optimizer: Prodigy / Cosine

Training was performed on Illustrious v1.1, so models within the Illustrious ecosystem pair most accurately with this LoRA.


Recommended Generation Settings

To get results that match the intended style:

  • Sampler: Euler_a

  • Steps: 30

  • CFG: 4.5


Positive Prompt Suggestions

These optional tags help guide the aesthetic:

film grain, film noir, cel shaded

Negative Prompt Suggestions

lowres, bad anatomy, bad hands, malformed hands, extra fingers, fused fingers, missing fingers, extra limbs, deformed, disfigured, multiple views, text, watermark, signature, username, copyright, error, jpeg artifacts, old, oldest, jaggy lines, latex, shiny skin, guro

Compatibility

This LoRA works well with the following checkpoint:


Support the Artist

Please consider following or supporting TerribleAnimal.
This LoRA was created to help their style reach new audiences across the AI art community.
Respect the original artist and credit them whenever appropriate.


Have a question or suggestion?

I can usually be reached on Discord at: piper260

此模型生成的图像