Commit
•
e160d1d
1
Parent(s):
6cb3dd2
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,14 +6,18 @@ pipeline_tag: text-to-image
|
|
| 6 |
|
| 7 |
This repository will serve as a location for uploading my personal LoRAs and Dreambooth models.
|
| 8 |
|
| 9 |
-
# Model Description
|
| 10 |
|
| 11 |
What is a LoRA? https://github.com/cloneofsimo/lora
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
| 14 |
|
| 15 |
Automatic1111's WebUI now has native LoRA support, and LoRAs can be activated by prompting \<lora:name_of_your_lora:network_weight\>
|
| 16 |
|
|
|
|
|
|
|
| 17 |
# Training Details
|
| 18 |
|
| 19 |
LoRAs trained locally using bmaltais GUI for kohya_ss sd-scripts:
|
|
@@ -28,23 +32,38 @@ https://huggingface.co/JosephusCheung/ACertainty
|
|
| 28 |
|
| 29 |
# Table of Contents
|
| 30 |
Persona 5
|
| 31 |
-
- [Ann Takamaki](#
|
| 32 |
-
- [Futaba Sakura](#
|
| 33 |
-
- [Haru Okumura](#
|
| 34 |
-
- [Kasumi Yoshizawa](#
|
| 35 |
-
- [Makoto Niijima](#
|
| 36 |
|
| 37 |
# Ann Takamaki
|
|
|
|
| 38 |
Instance Token: dsann
|
| 39 |
|
|
|
|
|
|
|
| 40 |
# Futaba Sakura
|
|
|
|
| 41 |
Instance Token: dsfutaba
|
| 42 |
|
|
|
|
|
|
|
| 43 |
# Haru Okumura
|
|
|
|
| 44 |
Instance Token: dsharu
|
| 45 |
|
|
|
|
|
|
|
| 46 |
# Kasumi Yoshizawa
|
|
|
|
| 47 |
Instance Token: dskasumi
|
| 48 |
|
|
|
|
|
|
|
| 49 |
# Makoto Niijima
|
| 50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
This repository will serve as a location for uploading my personal LoRAs and Dreambooth models.
|
| 8 |
|
| 9 |
+
# Model Description and Usage
|
| 10 |
|
| 11 |
What is a LoRA? https://github.com/cloneofsimo/lora
|
| 12 |
|
| 13 |
+
e1-e5 represent training length in number of epochs. You may need to lower the network weight on further trained LoRAs if the effects are too strong.
|
| 14 |
+
|
| 15 |
+
"legacy" LoRAs are approximations extracted from model diffs from my old Dreambooth models, included for completeness.
|
| 16 |
|
| 17 |
Automatic1111's WebUI now has native LoRA support, and LoRAs can be activated by prompting \<lora:name_of_your_lora:network_weight\>
|
| 18 |
|
| 19 |
+
If you are on an older version, you will need to use the additional networks extension to load LoRAs: https://github.com/kohya-ss/sd-webui-additional-networks
|
| 20 |
+
|
| 21 |
# Training Details
|
| 22 |
|
| 23 |
LoRAs trained locally using bmaltais GUI for kohya_ss sd-scripts:
|
|
|
|
| 32 |
|
| 33 |
# Table of Contents
|
| 34 |
Persona 5
|
| 35 |
+
- [Ann Takamaki](#ann-takamaki)
|
| 36 |
+
- [Futaba Sakura](#futaba-sakura)
|
| 37 |
+
- [Haru Okumura](#haru-okumura)
|
| 38 |
+
- [Kasumi Yoshizawa](#kasumi-yoshizawa)
|
| 39 |
+
- [Makoto Niijima](#makoto-niijima)
|
| 40 |
|
| 41 |
# Ann Takamaki
|
| 42 |
+
|
| 43 |
Instance Token: dsann
|
| 44 |
|
| 45 |
+
<img src="https://huggingface.co/Doctor-Shotgun/ds-LoRA/resolve/main/Previews/ann01.png" width="240" height="320" alt=”ann01”>
|
| 46 |
+
|
| 47 |
# Futaba Sakura
|
| 48 |
+
|
| 49 |
Instance Token: dsfutaba
|
| 50 |
|
| 51 |
+
<img src="https://huggingface.co/Doctor-Shotgun/ds-LoRA/resolve/main/Previews/futaba01.png" width="320" height="240" alt=”futaba01”>
|
| 52 |
+
|
| 53 |
# Haru Okumura
|
| 54 |
+
|
| 55 |
Instance Token: dsharu
|
| 56 |
|
| 57 |
+
<img src="https://huggingface.co/Doctor-Shotgun/ds-LoRA/resolve/main/Previews/haru01.png" width="240" height="320" alt=”haru01”>
|
| 58 |
+
|
| 59 |
# Kasumi Yoshizawa
|
| 60 |
+
|
| 61 |
Instance Token: dskasumi
|
| 62 |
|
| 63 |
+
<img src="https://huggingface.co/Doctor-Shotgun/ds-LoRA/resolve/main/Previews/kasumi01.png" width="240" height="320" alt=”kasumi01”>
|
| 64 |
+
|
| 65 |
# Makoto Niijima
|
| 66 |
+
|
| 67 |
+
Instance Token: dsmakoto
|
| 68 |
+
|
| 69 |
+
<img src="https://huggingface.co/Doctor-Shotgun/ds-LoRA/resolve/main/Previews/makoto01.png" width="320" height="240" alt=”makoto01”>
|