Hugging Face's logo

bghira
/
sd35m-photo-clip_value-shift3

Text-to-Image
Diffusers
Safetensors
sd3
sd3-diffusers
simpletuner
Not-For-All-Audiences
lora
template:sd-lora
lycoris
Model card Files Community
bghira commited on
Commit
093dabc
·
verified ·
1 Parent(s): 85d2d23

Model card auto-generated by SimpleTuner

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -329,7 +329,7 @@ You may reuse the base model text encoder for inference.
329
  ## Training settings
330
 
331
  - Training epochs: 2
332
- - Training steps: 318000
333
  - Learning rate: 5e-05
334
  - Learning rate schedule: constant
335
  - Warmup steps: 500
@@ -386,7 +386,7 @@ You may reuse the base model text encoder for inference.
386
  ### signs
387
  - Repeats: 150
388
  - Total number of images: ~420
389
- - Total number of aspect buckets: 10
390
  - Resolution: 1.048576 megapixels
391
  - Cropped: False
392
  - Crop style: None
@@ -395,7 +395,7 @@ You may reuse the base model text encoder for inference.
395
  ### moviecollection
396
  - Repeats: 0
397
  - Total number of images: ~1983
398
- - Total number of aspect buckets: 16
399
  - Resolution: 1.048576 megapixels
400
  - Cropped: False
401
  - Crop style: None
@@ -485,7 +485,7 @@ You may reuse the base model text encoder for inference.
485
  ### anatomy-512
486
  - Repeats: 5
487
  - Total number of images: ~16437
488
- - Total number of aspect buckets: 8
489
  - Resolution: 0.262144 megapixels
490
  - Cropped: False
491
  - Crop style: None
@@ -494,7 +494,7 @@ You may reuse the base model text encoder for inference.
494
  ### signs-1440
495
  - Repeats: 100
496
  - Total number of images: ~423
497
- - Total number of aspect buckets: 25
498
  - Resolution: 2.0736 megapixels
499
  - Cropped: False
500
  - Crop style: None
@@ -521,7 +521,7 @@ You may reuse the base model text encoder for inference.
521
  ### shutterstock-1440
522
  - Repeats: 0
523
  - Total number of images: ~21111
524
- - Total number of aspect buckets: 38
525
  - Resolution: 2.0736 megapixels
526
  - Cropped: False
527
  - Crop style: None
@@ -539,7 +539,7 @@ You may reuse the base model text encoder for inference.
539
  ### anatomy-1440
540
  - Repeats: 5
541
  - Total number of images: ~16458
542
- - Total number of aspect buckets: 9
543
  - Resolution: 2.0736 megapixels
544
  - Cropped: False
545
  - Crop style: None
 
329
  ## Training settings
330
 
331
  - Training epochs: 2
332
+ - Training steps: 319000
333
  - Learning rate: 5e-05
334
  - Learning rate schedule: constant
335
  - Warmup steps: 500
 
386
  ### signs
387
  - Repeats: 150
388
  - Total number of images: ~420
389
+ - Total number of aspect buckets: 14
390
  - Resolution: 1.048576 megapixels
391
  - Cropped: False
392
  - Crop style: None
 
395
  ### moviecollection
396
  - Repeats: 0
397
  - Total number of images: ~1983
398
+ - Total number of aspect buckets: 13
399
  - Resolution: 1.048576 megapixels
400
  - Cropped: False
401
  - Crop style: None
 
485
  ### anatomy-512
486
  - Repeats: 5
487
  - Total number of images: ~16437
488
+ - Total number of aspect buckets: 7
489
  - Resolution: 0.262144 megapixels
490
  - Cropped: False
491
  - Crop style: None
 
494
  ### signs-1440
495
  - Repeats: 100
496
  - Total number of images: ~423
497
+ - Total number of aspect buckets: 15
498
  - Resolution: 2.0736 megapixels
499
  - Cropped: False
500
  - Crop style: None
 
521
  ### shutterstock-1440
522
  - Repeats: 0
523
  - Total number of images: ~21111
524
+ - Total number of aspect buckets: 37
525
  - Resolution: 2.0736 megapixels
526
  - Cropped: False
527
  - Crop style: None
 
539
  ### anatomy-1440
540
  - Repeats: 5
541
  - Total number of images: ~16458
542
+ - Total number of aspect buckets: 7
543
  - Resolution: 2.0736 megapixels
544
  - Cropped: False
545
  - Crop style: None