adds loss values to most LoRAs

chise/README.md

@@ -31,6 +31,7 @@ For her swimsuit alt: `side ponytail, swimsuit, striped bikini, see-through, see
   - 9 repeats for swimsuit outfit
   - 3 batch size, 4 epochs
   - `(76*9 + 43*15) / 3 * 4` = 1772 steps
+- 0.0837 loss
 - 832x832 training resolution
 - `constant_with_warmup` scheduler
 - Initially tagged with WD1.4 Convnext-v2 model, then heavily edited.

koharu/README.md

@@ -36,6 +36,7 @@ Some of her swimsuits are in the training data, too.
   - 5 repeats for flustered expression outfit
   - 3 batch size, 7 epochs
   - `(170*4 + 13*5) / 3 * 7` = 1739 steps
+- 0.078 loss
 - 832x832 training resolution
 - `constant_with_warmup` scheduler
 - Initially tagged using scraped Danbooru tags, then heavily edited.

mari/README.md

@@ -38,6 +38,7 @@ For her swimsuit: `black one-piece swimsuit, frilled swimsuit, frills, paw print
   - 3 batch size, 7 epochs
   - `(253*3) / 3 * 7` = 1771 steps
   - Increased steps for stronger fit due to larger, more varied dataset.
+- 0.0823 loss
 - 768x768 training resolution
 - `constant_with_warmup` scheduler
 - Initially tagged with WD1.4 Convnext model, then heavily edited.

reisa/README.md

@@ -32,6 +32,7 @@ For her normal outfit: `school uniform, grey shirt, blue jacket, pleated skirt,
   - 13 repeats
   - 3 batch size, 4 epochs
   - `(89*13) / 3 * 4` = 1543 steps
+- 0.0743 loss
 - 768x768 training resolution
 - `constant_with_warmup` scheduler instead of `cosine`
 - Initially tagged with WD1.4 Convnextv2 model. Tags were edited for accuracy and improved outfit consistency.  Tags for facial expressions, camera angle, and image composition were added.

seia/README.md

@@ -31,6 +31,7 @@ For her expressions: `expressionless` / `light smile` / `parted lips`
   - 13 repeats
   - 3 batch size, 4 epochs
   - `(96 * 13) / 3 * 4` = 1664 steps
+- 0.0764 loss
 - Initially tagged with WD1.4 swin-v2 model. Tags pruned/edited for consistency.
 - `constant_with_warmup` scheduler
 - 1.5e-5 text encoder LR

shizuko/README.md

@@ -41,6 +41,7 @@ Her shotgun sling tends to show up on her normal outfit and is a little hard to
   - 8 repeats for swimsuit outfit
   - 3 batch size, 4 epochs
   - `(88*8 + 37*11) / 3 * 4` = 1482 steps
+- 0.0958 loss
 - Due to a change in the kohya GUI script, a few of my previous LoRAs (Mari, Michiru, Reisa, Sora, Chise) were accidentally trained without my painstakingly pruned tags.  This is probably why they seem overfit to the characters' outfits, though the results were surprisingly good considering there were literally no tags.
 - Once I found this issue, I figured since I'd have to "re-learn" some of my settings anyway to account for proper captions, I may as well experiment with batch/dim/alpha/LR valuee.  Unfortunately, no conclusive results.  Ended up going back to tried and true settings from several LoRAs ago.  
 - `constant_with_warmup` scheduler instead of `cosine` since it seems to train in fewer steps, at the cost of being more finnicky

sora/README.md

@@ -33,6 +33,7 @@ Weight 1 is suggested.
   - 9 repeats
   - 3 batch size, 4 epochs
   - `(128*9) / 3 * 4` = 1536 steps
+- 0.0791 loss
 - 768x768 training resolution
 - `constant_with_warmup` scheduler instead of `cosine`
 - Initially tagged with WD1.4 Convnextv2 model. Tags minimally pruned/edited.