Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
3 |
---
|
|
|
1 |
+
Additional learning was done with illustrations generated by niji-journey to create LoRA. The trigger word is "jis".
|
2 |
+
It is based on various models. Files are different for each base model.
|
3 |
+
niji2:Own merge model zzzmix(https://huggingface.co/zzzAI19/zzzmix)
|
4 |
+
niji2animekawa:AnimeKawa (https://civitai.com/models/87661/animekawa?modelVersionId=93295)
|
5 |
+
niji2anything:Anything v5 (https://civitai.com/models/9409/or-anything-v5ink)
|
6 |
+
niji2beautifulRealistic:Beautiful Realistic Asians (https://civitai.com/models/25494/brabeautiful-realistic-asians-v2)
|
7 |
+
niji2chilooutmix:chilloutmix (https://civitai.com/models/6424/chilloutmix)
|
8 |
+
niji2counterfeit:counterfeit v3 (https://huggingface.co/gsdf/Counterfeit-V3.0)
|
9 |
+
|
10 |
+
I also plan to use TrinArt, Irismix, chilled_remix, and openjourney as base models in the future.
|
11 |
+
LoRA with these models as base models will be uploaded tomorrow.
|
12 |
+
I would recommend a LoRA strength of 0.7. We also consider step 6 to be a good choice.
|
13 |
+
Sample images can be found at
|
14 |
+
https://ai-drawing.net/en/2023/07/05/introduction-of-niji-lora-v2-0/
|
15 |
+
|
16 |
+
|
17 |
+
niji・journeyにより生成されたイラストで追加学習し、LoRAを作りました。トリガーワードは「jis」です。
|
18 |
+
色々なモデルをベースにしています。ベースモデルごとにファイルが異なります。
|
19 |
+
niji2:自作マージモデルzzzmix(https://huggingface.co/zzzAI19/zzzmix)
|
20 |
+
niji2animekawa:AnimeKawa (https://civitai.com/models/87661/animekawa?modelVersionId=93295)
|
21 |
+
niji2anything:Anything v5 (https://civitai.com/models/9409/or-anything-v5ink)
|
22 |
+
niji2beautifulRealistic:Beautiful Realistic Asians (https://civitai.com/models/25494/brabeautiful-realistic-asians-v2)
|
23 |
+
niji2chilooutmix:chilloutmix (https://civitai.com/models/6424/chilloutmix)
|
24 |
+
niji2counterfeit:counterfeit v3 (https://huggingface.co/gsdf/Counterfeit-V3.0)
|
25 |
+
|
26 |
+
また今後、TrinArt、Irismix、chilled_remix、openjourneyもベースモデルにする予定です。
|
27 |
+
これらのモデルをベースモデルとしたLoRAは明日アップロードする予定です。
|
28 |
+
|
29 |
+
LoRA強度は0.7を推奨します。 またステップ6が良いと考えます。
|
30 |
+
サンプル画像は以下のページにあります。
|
31 |
+
https://ai-drawing.net/2023/07/05/niji-lora-v2-0%e3%81%ae%e7%b4%b9%e4%bb%8b/
|
32 |
+
|
33 |
+
|
34 |
---
|
35 |
license: creativeml-openrail-m
|
36 |
---
|