Dreambooth for people in a hurry - Colab edition

The Stable-Diffusion-v1-5 checkpoint is used as base model, and trained with custom concept.

Concept info

Your full token: <b>x_boonsie woman</b> Example prompt: Professional headshot photo of x_boonsie woman as a magician, Tiffen Digital Diffusion / FX, 100mm

Instance prompt: photo of x_boonsie woman Class prompt: photo of a woman

Model info

Training images: 6 Regularization images: 50 Model type: Diffusers, Checkpoint

training_steps: 1000 lr_scheduler: constant lr_warmup_steps: 0 learning rate: 1e-6 mixed_precision: fp16