Use at Clip Skip 2

Retrolux

Trigger Word: Not necessary,

Training Configuration:

GPU: L40

Dataset Size: 789 images

Batch Size: 2

Optimizer: AdamW8bit

Learning Rate: 1e-05

Recommended Parameters:

Sampler: Euler A

Steps: 25 ↔️ 30.

CFG Scale: 2.0 ↔️ 6.0

Clip Skip : 2

🌐 Any inquiries about my model are more than welcome. Reach out on Discord ➡️ shopon_skp. Let's keep the conversation going