Model card auto-generated by SimpleTuner

README.md

@@ -330,8 +330,8 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 14000
-- Learning rate: 1.0
+- Training steps: 1000
+- Learning rate: 5e-05
   - Learning rate schedule: cosine
   - Warmup steps: 400000
 - Max grad norm: 0.0
@@ -341,7 +341,7 @@ You may reuse the base model text encoder for inference.
   - Number of GPUs: 3
 - Gradient checkpointing: True
 - Prediction type: flow-matching (extra parameters=['shift=3.0'])
-- Optimizer: prodigyd0=1e-5
+- Optimizer: adamw_bf16
 - Trainable parameter precision: Pure BF16
 - Caption dropout probability: 10.0%
 
@@ -375,91 +375,10 @@ You may reuse the base model text encoder for inference.
 
 ## Datasets
 
-### comicstrips
-- Repeats: 50
-- Total number of images: ~1470
-- Total number of aspect buckets: 1
-- Resolution: 1.048576 megapixels
-- Cropped: False
-- Crop style: None
-- Crop aspect: None
-- Used for regularisation data: No
-### normalnudes
-- Repeats: 50
-- Total number of images: ~1278
-- Total number of aspect buckets: 32
-- Resolution: 1.048576 megapixels
-- Cropped: False
-- Crop style: None
-- Crop aspect: None
-- Used for regularisation data: No
-### nsfw-1024
-- Repeats: 50
-- Total number of images: ~10830
-- Total number of aspect buckets: 1
-- Resolution: 1.048576 megapixels
-- Cropped: False
-- Crop style: None
-- Crop aspect: None
-- Used for regularisation data: No
-### yoga
-- Repeats: 50
-- Total number of images: ~3642
-- Total number of aspect buckets: 2
-- Resolution: 1.048576 megapixels
-- Cropped: False
-- Crop style: None
-- Crop aspect: None
-- Used for regularisation data: No
-### text-1mp-v2
+### celebrities
 - Repeats: 100
-- Total number of images: ~13221
-- Total number of aspect buckets: 5
-- Resolution: 1.048576 megapixels
-- Cropped: False
-- Crop style: None
-- Crop aspect: None
-- Used for regularisation data: No
-### signs-v2
-- Repeats: 150
-- Total number of images: ~420
-- Total number of aspect buckets: 8
-- Resolution: 1.048576 megapixels
-- Cropped: False
-- Crop style: None
-- Crop aspect: None
-- Used for regularisation data: No
-### moviecollection-v2
-- Repeats: 0
-- Total number of images: ~1983
-- Total number of aspect buckets: 34
-- Resolution: 1.048576 megapixels
-- Cropped: False
-- Crop style: None
-- Crop aspect: None
-- Used for regularisation data: No
-### bookcovers-v2
-- Repeats: 0
-- Total number of images: ~927
-- Total number of aspect buckets: 26
-- Resolution: 1.048576 megapixels
-- Cropped: False
-- Crop style: None
-- Crop aspect: None
-- Used for regularisation data: No
-### shutterstock-v2
-- Repeats: 0
-- Total number of images: ~21111
-- Total number of aspect buckets: 20
-- Resolution: 1.048576 megapixels
-- Cropped: False
-- Crop style: None
-- Crop aspect: None
-- Used for regularisation data: No
-### cinemamix-1mp-v2
-- Repeats: 0
-- Total number of images: ~7425
-- Total number of aspect buckets: 5
+- Total number of images: ~3921
+- Total number of aspect buckets: 1
 - Resolution: 1.048576 megapixels
 - Cropped: False
 - Crop style: None