Update README.md
Browse files
README.md
CHANGED
@@ -11,37 +11,40 @@ base_model:
|
|
11 |
|
12 |
Fine-tuned NoobAI-XL(v-prediction) and merged SPO
|
13 |
|
14 |
-
|
15 |
-
|
16 |
-
|
|
|
|
|
17 |
- ReForge on `dev_upstream_experimental` branch
|
18 |
|
19 |
### Instruction for AUTOMATIC1111
|
20 |
-
1.
|
21 |
-
2.
|
22 |
-
3.
|
|
|
23 |
|
24 |
### Instruction for ReForge
|
25 |
-
1.
|
26 |
-
2.
|
27 |
-
3.
|
28 |
-
4.
|
|
|
29 |
|
30 |
-
### Example Workflow for ComfyUI
|
31 |
Download it from [here](https://files.catbox.moe/v0isof.png)
|
32 |
|
33 |
-
## Prompt Guidelines
|
34 |
-
Almost same as the base model
|
35 |
|
36 |
To improve the quality of background, add `simple background, transparent background` to Negative Prompt.
|
37 |
|
38 |
-
## Recommended Prompt
|
39 |
-
|
40 |
-
Positive: None(Works good without `masterpiece, best quality`)
|
41 |
|
42 |
Negative: `worst quality, low quality, bad quality, lowres, jpeg artifacts, unfinished, oldest, old, photoshop \(medium\), abstract`
|
43 |
|
44 |
-
## Recommended Settings
|
45 |
Steps: 14-28
|
46 |
|
47 |
Sampler: DPM++ 2M(dpmpp_2m)
|
@@ -83,4 +86,17 @@ This model is licensed under [Fair AI Public License 1.0-SD](https://freedevproj
|
|
83 |
|
84 |
If you make modify this model, you must share both your changes and the original license.
|
85 |
|
86 |
-
You are prohibited from monetizing any close-sourced fine-tuned / merged model, which disallows the public from accessing the model's source code / weights and its usages.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
Fine-tuned NoobAI-XL(v-prediction) and merged SPO
|
13 |
|
14 |
+
日本語での導入手順はページ下部にあります。
|
15 |
+
|
16 |
+
## Requirements / 動作要件
|
17 |
+
- AUTOMATIC1111 WebUI on `dev` branch / devブランチ上のAUTOMATIC1111 WebUI
|
18 |
+
- Latest version of ComfyUI / 最新版のComfyUI
|
19 |
- ReForge on `dev_upstream_experimental` branch
|
20 |
|
21 |
### Instruction for AUTOMATIC1111
|
22 |
+
1. Download the model
|
23 |
+
2. Switch branch to `dev`
|
24 |
+
3. Copy `configs/sd_xl_v.yaml` to `models/Stable-Diffusion/`
|
25 |
+
4. Rename it to the same as the model name
|
26 |
|
27 |
### Instruction for ReForge
|
28 |
+
1. Download the model
|
29 |
+
2. Switch branch to `dev_upstream_experimental`
|
30 |
+
3. Find “Advanced Model Sampling for Forge” at the bottom of the page
|
31 |
+
4. Enable “Enable Advanced Model Sampling”
|
32 |
+
5. Select `v_prediction` in Discrete Sampling Type
|
33 |
|
34 |
+
### Example Workflow for ComfyUI / ComfyUIサンプルワークフロー
|
35 |
Download it from [here](https://files.catbox.moe/v0isof.png)
|
36 |
|
37 |
+
## Prompt Guidelines / プロンプト記法
|
38 |
+
Almost same as the base model/ベースモデルとおおむね同じ
|
39 |
|
40 |
To improve the quality of background, add `simple background, transparent background` to Negative Prompt.
|
41 |
|
42 |
+
## Recommended Prompt / 推奨プロンプト
|
43 |
+
Positive: None/無し(Works good without `masterpiece, best quality` / `masterpiece, best quality`無しでおk)
|
|
|
44 |
|
45 |
Negative: `worst quality, low quality, bad quality, lowres, jpeg artifacts, unfinished, oldest, old, photoshop \(medium\), abstract`
|
46 |
|
47 |
+
## Recommended Settings / 推奨設定
|
48 |
Steps: 14-28
|
49 |
|
50 |
Sampler: DPM++ 2M(dpmpp_2m)
|
|
|
86 |
|
87 |
If you make modify this model, you must share both your changes and the original license.
|
88 |
|
89 |
+
You are prohibited from monetizing any close-sourced fine-tuned / merged model, which disallows the public from accessing the model's source code / weights and its usages.
|
90 |
+
|
91 |
+
### AUTOMATIC1111の導入手順
|
92 |
+
1. devブランチに切り替える(ブランチの切り替えかたは各自調べてください)。
|
93 |
+
2. モデルをダウンロードする。
|
94 |
+
3. `configs/sd_xl_v.yaml`を`models/Stable-Diffusion/`にコピーする
|
95 |
+
4. コピペしたファイルをモデル名と同名にする
|
96 |
+
|
97 |
+
### ReForgeの導入手順
|
98 |
+
1. `dev_upstream_experimental`ブランチに切り替える
|
99 |
+
2. モデルをダウンロードする。
|
100 |
+
3. WebUIのページ下部から“Advanced Model Sampling for Forge”を見つける
|
101 |
+
4. “Enable Advanced Model Sampling”を有効にする
|
102 |
+
5. Discrete Sampling Typeを`v_prediction`にする
|