Upload 5 files

.gitattributes

@@ -38,3 +38,4 @@ on_crescent_previews/70677-2928894193-on_crescent,[[:space:]]hatsune[[:space:]]m
 on_crescent_previews/70693-836700246-on_crescent,[[:space:]]1girl,[[:space:]]((solo[[:space:]]focus)),[[:space:]]long[[:space:]]hair,[[:space:]](sitting[[:space:]]on[[:space:]]a[[:space:]]crescent[[:space:]]moon_1.1),[[:space:]](aerial[[:space:]]fireworks_1.2),[[:space:]]backlighting,[[:space:]]smile,[[:space:]]st.png filter=lfs diff=lfs merge=lfs -text
 on_crescent_previews/70708-1334998184-(on_crescent_1.2),[[:space:]](silhouette_1.15),[[:space:]]1girl,[[:space:]]long[[:space:]]hair,[[:space:]]floating[[:space:]]hair,[[:space:]](red[[:space:]]hair_1.15),[[:space:]]sidelocks,[[:space:]]dark[[:space:]]background,[[:space:]]mid[[:space:]]shot,[[:space:]]so.png filter=lfs diff=lfs merge=lfs -text
 on_crescent_previews/70721-4047128455-(on_crescent_1.2),[[:space:]]monster[[:space:]]hunter[[:space:]]_(series_),[[:space:]](sitting[[:space:]]on[[:space:]]the[[:space:]]crescent[[:space:]]moon_1.1),[[:space:]](masterpiece_1.1),[[:space:]]highres,[[:space:]]absurdres,[[:space:]]beautif.png filter=lfs diff=lfs merge=lfs -text
+Not[[:space:]]Mine/bluethebone-1902it-novae.png filter=lfs diff=lfs merge=lfs -text

Not Mine/bluethebone-1902it-novae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3534716b00e2dc4177751c572082785c9a9e74d9aade2167e9406651ddd9d207
+size 154560134

Not Mine/bluethebone-1902it-novae.txt

@@ -0,0 +1,70 @@
+1902it
+
+317 images
+6 repeats
+
+4 batchsize
+3 epochs
+1902it total
+
+3.2e-4 learning rate
+4e-5 text_encoder
+3.2e-4 unet_lr
+768 res
+128 dim
+128 network_alpha
+
+wd14 swinv2 v2 interrogator
+no vae 
+0 keeptokens
+
+got some interesting results with different learning rates on this one.
+>multiply 8e-5 by batch_size for unet_lr. set unet_lr as learning_rate also.
+>multiply 1.5e-5 by your batch_size for text_encoder_lr.
+>batch size 4 has unet at 3.2e-4 and text encoder 6e-5.
+
+training notes i took in the process of adjusting rates:
+
+the original parameters i trained with were my default (lr 2e-6, text 5e-5, and unet 1.5e-4).
+this as usual worked fairly well, though i wanted to mess around with learning rates to see if it would make a difference. for the next set, i used the instructions in the greentext above and adjusted to newer learning rates.
+the main goal was improving the style while 
+
+=v1=
+novae		old		new		delta
+lr = 		2e-6		3.2e-4		increase
+text = 		5e-5		6e-5		increase
+unet = 		1.5e-4		3.2e-4		increase	
+
+observed changes:
+black thighhighs turned white at 1.0
+short hair in prompt ignored (turned long)
+background more consistent with older (lr)
+
+
+=v2=
+novae		old		new		delta
+lr = 		3.2e-4		3.2e-4		0
+text = 		6e-5		5e-5		decrease
+unet = 		3.2e-4		3.2e-4		0	
+
+observed changes:
+short hair is no longer ignored (fixed)
+black thighhighs still turn white
+background is closer to weight 0
+
+=v3=
+novae		old		new		delta
+lr = 		3.2e-4		3.2e-4		0
+text = 		5e-5		4e-5		decrease
+unet = 		3.2e-4		3.2e-4		0
+
+observed changes:
+short hair is still fixed
+white thighhighs are fixed; they are now black
+
+this is the final version that is uploaded. in v1, the changes made to the learning rate incorporated more of the artists style while also not following the prompt as well; the thighhighs were white and the hair was no longer short. i figured this was due to the increase in all the learning rate settings overall from the original. to compensate for this, text_encoder lr was lowered from 6e-5 to 5e-5. this fixed the issue with the hair but did not fix the thighhighs. v3 lowered text_encoder lr to 4e-5, which seemed to do the trick. overall, the differences between the original version and the final one are slight, but it does incorporate more of the style while also adhering to the prompt, which was the goal.
+
+
+
+
+

Not Mine/khyle-2192it-novae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd9a1352ab35245d7883570209f6feca8147bf7cf57a9fdc93951006050bf46
+size 151074581

Not Mine/khyle-2192it-novae.txt

@@ -0,0 +1,19 @@
+2192it:
+
+274 images
+4 repeats
+
+4 batchsize
+8 epochs
+2192it total
+
+2e-6 learning rate (default)
+5e-5 text_encoder
+1.5e-4 unet_lr
+768 res
+128 dim
+128 network alpha
+
+wd14 vit v1 interrogator
+kl-f8-anime2 vae 
+0 keeptokens