updates README for several characters
Browse files- arona/README.md +0 -1
- mari/README.md +0 -1
- mutsuki/README.md +0 -1
- reisa/README.md +0 -1
- shizuko/README.md +0 -1
- sora/README.md +0 -1
arona/README.md
CHANGED
|
@@ -34,7 +34,6 @@ Not all tags may be necessary.
|
|
| 34 |
## Training
|
| 35 |
*Exact parameters are provided in the accompanying JSON files.*
|
| 36 |
- Trained on a set of 250 images.
|
| 37 |
-
- Datset included a mixture of SFW/NSFW
|
| 38 |
- 5 repeats
|
| 39 |
- 3 batch size, 4 epochs
|
| 40 |
- `(250 * 5) / 3 * 4` = 1667 steps
|
| 34 |
## Training
|
| 35 |
*Exact parameters are provided in the accompanying JSON files.*
|
| 36 |
- Trained on a set of 250 images.
|
|
|
|
| 37 |
- 5 repeats
|
| 38 |
- 3 batch size, 4 epochs
|
| 39 |
- `(250 * 5) / 3 * 4` = 1667 steps
|
mari/README.md
CHANGED
|
@@ -34,7 +34,6 @@ For her swimsuit: `black one-piece swimsuit, frilled swimsuit, frills, paw print
|
|
| 34 |
## Training
|
| 35 |
*Exact parameters are provided in the accompanying JSON files.*
|
| 36 |
- Trained on a set of 253 images
|
| 37 |
-
- Datset included a mixture of SFW/NSFW.
|
| 38 |
- 3 repeats
|
| 39 |
- 3 batch size, 7 epochs
|
| 40 |
- `(253*3) / 3 * 7` = 1771 steps
|
| 34 |
## Training
|
| 35 |
*Exact parameters are provided in the accompanying JSON files.*
|
| 36 |
- Trained on a set of 253 images
|
|
|
|
| 37 |
- 3 repeats
|
| 38 |
- 3 batch size, 7 epochs
|
| 39 |
- `(253*3) / 3 * 7` = 1771 steps
|
mutsuki/README.md
CHANGED
|
@@ -3,7 +3,6 @@ This is my first time doing any sort of Stable Diffusion training so I went thro
|
|
| 3 |
# Training
|
| 4 |
*All parameters are provided in the accompanying JSON files.*
|
| 5 |
- Trained on 138 curated images, repeated 8 times (1104 total images / 3 batchsize = 368 iterations)
|
| 6 |
-
- Dataset included a mixture of SFW and NSFW
|
| 7 |
- I pruned most images with white backgrounds because I felt they might have been negatively impacting my results early on, but in hindsight I think that was bad training parameters instead.
|
| 8 |
- Dataset was tagged with WD1.4 interrogator. Shuffling was disabled.
|
| 9 |
- `mutsuki, blue archive` were added to the start of each caption.
|
| 3 |
# Training
|
| 4 |
*All parameters are provided in the accompanying JSON files.*
|
| 5 |
- Trained on 138 curated images, repeated 8 times (1104 total images / 3 batchsize = 368 iterations)
|
|
|
|
| 6 |
- I pruned most images with white backgrounds because I felt they might have been negatively impacting my results early on, but in hindsight I think that was bad training parameters instead.
|
| 7 |
- Dataset was tagged with WD1.4 interrogator. Shuffling was disabled.
|
| 8 |
- `mutsuki, blue archive` were added to the start of each caption.
|
reisa/README.md
CHANGED
|
@@ -29,7 +29,6 @@ For her normal outfit: `school uniform, grey shirt, blue jacket, pleated skirt,
|
|
| 29 |
## Training
|
| 30 |
*Exact parameters are provided in the accompanying JSON files.*
|
| 31 |
- Trained on a set of 89 images
|
| 32 |
-
- Datset included a mixture of SFW/NSFW
|
| 33 |
- 13 repeats
|
| 34 |
- 3 batch size, 4 epochs
|
| 35 |
- `(89*13) / 3 * 4` = 1543 steps
|
| 29 |
## Training
|
| 30 |
*Exact parameters are provided in the accompanying JSON files.*
|
| 31 |
- Trained on a set of 89 images
|
|
|
|
| 32 |
- 13 repeats
|
| 33 |
- 3 batch size, 4 epochs
|
| 34 |
- `(89*13) / 3 * 4` = 1543 steps
|
shizuko/README.md
CHANGED
|
@@ -37,7 +37,6 @@ Her shotgun sling tends to show up on her normal outfit and is a little hard to
|
|
| 37 |
## Training
|
| 38 |
*Exact parameters are provided in the accompanying JSON files.*
|
| 39 |
- Trained on a set of 125 images; 88 swimsuit, 37 normal.
|
| 40 |
-
- Datset included a mixture of SFW/NSFW
|
| 41 |
- 11 repeats for normal outfit
|
| 42 |
- 8 repeats for swimsuit outfit
|
| 43 |
- 3 batch size, 4 epochs
|
| 37 |
## Training
|
| 38 |
*Exact parameters are provided in the accompanying JSON files.*
|
| 39 |
- Trained on a set of 125 images; 88 swimsuit, 37 normal.
|
|
|
|
| 40 |
- 11 repeats for normal outfit
|
| 41 |
- 8 repeats for swimsuit outfit
|
| 42 |
- 3 batch size, 4 epochs
|
sora/README.md
CHANGED
|
@@ -32,7 +32,6 @@ Weight 1 is suggested.
|
|
| 32 |
## Training
|
| 33 |
*Exact parameters are provided in the accompanying JSON files.*
|
| 34 |
- Trained on a set of 128 images
|
| 35 |
-
- Datset included a mixture of SFW/NSFW. Sora has more NSFW than most students.
|
| 36 |
- 9 repeats
|
| 37 |
- 3 batch size, 4 epochs
|
| 38 |
- `(128*9) / 3 * 4` = 1536 steps
|
| 32 |
## Training
|
| 33 |
*Exact parameters are provided in the accompanying JSON files.*
|
| 34 |
- Trained on a set of 128 images
|
|
|
|
| 35 |
- 9 repeats
|
| 36 |
- 3 batch size, 4 epochs
|
| 37 |
- `(128*9) / 3 * 4` = 1536 steps
|