Hugging Face's logo

bghira
/
sd35m-photo-SLG-shift0.8-attn_ff-512to2048px

Text-to-Image
Diffusers
sd3
sd3-diffusers
simpletuner
Not-For-All-Audiences
lora
template:sd-lora
standard
Model card Files Community
bghira commited on
Commit
dc44ef1
·
verified ·
1 Parent(s): c1b2b8b

Model card auto-generated by SimpleTuner

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -330,7 +330,7 @@ You may reuse the base model text encoder for inference.
330
  ## Training settings
331
 
332
  - Training epochs: 1
333
- - Training steps: 62000
334
  - Learning rate: 0.0003
335
  - Learning rate schedule: constant
336
  - Warmup steps: 500
@@ -365,7 +365,7 @@ You may reuse the base model text encoder for inference.
365
  ### moviecollection
366
  - Repeats: 0
367
  - Total number of images: ~1983
368
- - Total number of aspect buckets: 14
369
  - Resolution: 1.048576 megapixels
370
  - Cropped: False
371
  - Crop style: None
@@ -383,7 +383,7 @@ You may reuse the base model text encoder for inference.
383
  ### shutterstock
384
  - Repeats: 0
385
  - Total number of images: ~21111
386
- - Total number of aspect buckets: 8
387
  - Resolution: 1.048576 megapixels
388
  - Cropped: False
389
  - Crop style: None
@@ -401,7 +401,7 @@ You may reuse the base model text encoder for inference.
401
  ### anatomy
402
  - Repeats: 5
403
  - Total number of images: ~16440
404
- - Total number of aspect buckets: 6
405
  - Resolution: 1.048576 megapixels
406
  - Cropped: False
407
  - Crop style: None
@@ -419,7 +419,7 @@ You may reuse the base model text encoder for inference.
419
  ### moviecollection-512
420
  - Repeats: 0
421
  - Total number of images: ~1971
422
- - Total number of aspect buckets: 5
423
  - Resolution: 0.262144 megapixels
424
  - Cropped: False
425
  - Crop style: None
@@ -455,7 +455,7 @@ You may reuse the base model text encoder for inference.
455
  ### anatomy-512
456
  - Repeats: 5
457
  - Total number of images: ~16437
458
- - Total number of aspect buckets: 7
459
  - Resolution: 0.262144 megapixels
460
  - Cropped: False
461
  - Crop style: None
@@ -464,7 +464,7 @@ You may reuse the base model text encoder for inference.
464
  ### signs-1440
465
  - Repeats: 100
466
  - Total number of images: ~423
467
- - Total number of aspect buckets: 25
468
  - Resolution: 2.0736 megapixels
469
  - Cropped: False
470
  - Crop style: None
@@ -473,7 +473,7 @@ You may reuse the base model text encoder for inference.
473
  ### moviecollection-1440
474
  - Repeats: 0
475
  - Total number of images: ~2007
476
- - Total number of aspect buckets: 34
477
  - Resolution: 2.0736 megapixels
478
  - Cropped: False
479
  - Crop style: None
@@ -482,7 +482,7 @@ You may reuse the base model text encoder for inference.
482
  ### bookcovers-1440
483
  - Repeats: 0
484
  - Total number of images: ~933
485
- - Total number of aspect buckets: 7
486
  - Resolution: 2.0736 megapixels
487
  - Cropped: False
488
  - Crop style: None
@@ -491,7 +491,7 @@ You may reuse the base model text encoder for inference.
491
  ### shutterstock-1440
492
  - Repeats: 0
493
  - Total number of images: ~21111
494
- - Total number of aspect buckets: 9
495
  - Resolution: 2.0736 megapixels
496
  - Cropped: False
497
  - Crop style: None
@@ -509,7 +509,7 @@ You may reuse the base model text encoder for inference.
509
  ### anatomy-1440
510
  - Repeats: 5
511
  - Total number of images: ~16458
512
- - Total number of aspect buckets: 7
513
  - Resolution: 2.0736 megapixels
514
  - Cropped: False
515
  - Crop style: None
 
330
  ## Training settings
331
 
332
  - Training epochs: 1
333
+ - Training steps: 63000
334
  - Learning rate: 0.0003
335
  - Learning rate schedule: constant
336
  - Warmup steps: 500
 
365
  ### moviecollection
366
  - Repeats: 0
367
  - Total number of images: ~1983
368
+ - Total number of aspect buckets: 9
369
  - Resolution: 1.048576 megapixels
370
  - Cropped: False
371
  - Crop style: None
 
383
  ### shutterstock
384
  - Repeats: 0
385
  - Total number of images: ~21111
386
+ - Total number of aspect buckets: 7
387
  - Resolution: 1.048576 megapixels
388
  - Cropped: False
389
  - Crop style: None
 
401
  ### anatomy
402
  - Repeats: 5
403
  - Total number of images: ~16440
404
+ - Total number of aspect buckets: 3
405
  - Resolution: 1.048576 megapixels
406
  - Cropped: False
407
  - Crop style: None
 
419
  ### moviecollection-512
420
  - Repeats: 0
421
  - Total number of images: ~1971
422
+ - Total number of aspect buckets: 3
423
  - Resolution: 0.262144 megapixels
424
  - Cropped: False
425
  - Crop style: None
 
455
  ### anatomy-512
456
  - Repeats: 5
457
  - Total number of images: ~16437
458
+ - Total number of aspect buckets: 4
459
  - Resolution: 0.262144 megapixels
460
  - Cropped: False
461
  - Crop style: None
 
464
  ### signs-1440
465
  - Repeats: 100
466
  - Total number of images: ~423
467
+ - Total number of aspect buckets: 16
468
  - Resolution: 2.0736 megapixels
469
  - Cropped: False
470
  - Crop style: None
 
473
  ### moviecollection-1440
474
  - Repeats: 0
475
  - Total number of images: ~2007
476
+ - Total number of aspect buckets: 24
477
  - Resolution: 2.0736 megapixels
478
  - Cropped: False
479
  - Crop style: None
 
482
  ### bookcovers-1440
483
  - Repeats: 0
484
  - Total number of images: ~933
485
+ - Total number of aspect buckets: 6
486
  - Resolution: 2.0736 megapixels
487
  - Cropped: False
488
  - Crop style: None
 
491
  ### shutterstock-1440
492
  - Repeats: 0
493
  - Total number of images: ~21111
494
+ - Total number of aspect buckets: 7
495
  - Resolution: 2.0736 megapixels
496
  - Cropped: False
497
  - Crop style: None
 
509
  ### anatomy-1440
510
  - Repeats: 5
511
  - Total number of images: ~16458
512
+ - Total number of aspect buckets: 4
513
  - Resolution: 2.0736 megapixels
514
  - Cropped: False
515
  - Crop style: None