Artist Style LoRA for Tres-art

Description:

This is an artist style LoRA of Tres-art.

Training Settings:

• Optimizer: Prodigy / Cosine

• Base Model: Illustrious v1.1

• Final Model: WAI

• Trigger Word(s): tr3s-ar7

• Training Steps/Epochs: 3105/27 (Clip skip 2)

• Dataset Size: 69

• Recommended Weight: 0.9-1.1 (1.0)

Sampler Settings:

• Steps: 30

• CFG: 4.5

• Sampler: Euler_a

Style positive design trigger words:

sharp detail, film grain, countershading, bloom, depth of field, saturated

Character negative design trigger words:

Suggested Resources:

https://civitai.com/models/1001945 - (Detail Slider IL)

https://civitai.com/models/827184?modelVersionId=1612720 - WAI Checkpoint

Please remember to follow/support the artist if possible.