|
--- |
|
license: mit |
|
--- |
|
## 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_sks_hastin_ring ring</b> |
|
Example prompt: Professional headshot photo of x_sks_hastin_ring ring as a magician, Tiffen Digital Diffusion / FX, 100mm |
|
|
|
Instance prompt: photo of x_sks_hastin_ring ring |
|
Class prompt: photo of a ring |
|
|
|
### Model info |
|
|
|
Training images: 8 |
|
Regularization images: 50 |
|
Model type: Diffusers, Checkpoint |
|
|
|
training_steps: 1000 |
|
lr_scheduler: constant |
|
lr_warmup_steps: 0 |
|
learning rate: 1e-6 |
|
mixed_precision: bf16 |
|
|
|
|
