Text-to-Image
Diffusers
sd3
sd3-diffusers
simpletuner
Not-For-All-Audiences
lora
template:sd-lora
lycoris
Model card auto-generated by SimpleTuner
Browse files
README.md
CHANGED
|
@@ -330,7 +330,7 @@ You may reuse the base model text encoder for inference.
|
|
| 330 |
## Training settings
|
| 331 |
|
| 332 |
- Training epochs: 10
|
| 333 |
-
- Training steps:
|
| 334 |
- Learning rate: 0.0001
|
| 335 |
- Max grad norm: 0.01
|
| 336 |
- Effective batch size: 12
|
|
@@ -393,7 +393,7 @@ You may reuse the base model text encoder for inference.
|
|
| 393 |
### bookcovers
|
| 394 |
- Repeats: 0
|
| 395 |
- Total number of images: ~927
|
| 396 |
-
- Total number of aspect buckets:
|
| 397 |
- Resolution: 1.048576 megapixels
|
| 398 |
- Cropped: False
|
| 399 |
- Crop style: None
|
|
@@ -420,7 +420,7 @@ You may reuse the base model text encoder for inference.
|
|
| 420 |
### anatomy
|
| 421 |
- Repeats: 5
|
| 422 |
- Total number of images: ~16440
|
| 423 |
-
- Total number of aspect buckets:
|
| 424 |
- Resolution: 1.048576 megapixels
|
| 425 |
- Cropped: False
|
| 426 |
- Crop style: None
|
|
|
|
| 330 |
## Training settings
|
| 331 |
|
| 332 |
- Training epochs: 10
|
| 333 |
+
- Training steps: 118000
|
| 334 |
- Learning rate: 0.0001
|
| 335 |
- Max grad norm: 0.01
|
| 336 |
- Effective batch size: 12
|
|
|
|
| 393 |
### bookcovers
|
| 394 |
- Repeats: 0
|
| 395 |
- Total number of images: ~927
|
| 396 |
+
- Total number of aspect buckets: 1
|
| 397 |
- Resolution: 1.048576 megapixels
|
| 398 |
- Cropped: False
|
| 399 |
- Crop style: None
|
|
|
|
| 420 |
### anatomy
|
| 421 |
- Repeats: 5
|
| 422 |
- Total number of images: ~16440
|
| 423 |
+
- Total number of aspect buckets: 2
|
| 424 |
- Resolution: 1.048576 megapixels
|
| 425 |
- Cropped: False
|
| 426 |
- Crop style: None
|