Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,89 @@
|
|
1 |
-
---
|
2 |
-
license: other
|
3 |
-
license_name: faipl-1.0-sd
|
4 |
-
license_link: https://freedevproject.org/faipl-1.0-sd/
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: faipl-1.0-sd
|
4 |
+
license_link: https://freedevproject.org/faipl-1.0-sd/
|
5 |
+
base_model:
|
6 |
+
- RedRayz/illumina-noob-vpd
|
7 |
+
tags:
|
8 |
+
- stable-diffusion
|
9 |
+
- sdxl
|
10 |
+
---
|
11 |
+
|
12 |
+
# Abydos-NoovVpd-0.5
|
13 |
+
|
14 |
+
Constructing...
|
15 |
+
|
16 |
+
Fine-tuned NoobAI-XL(v-prediction) and merged SPO
|
17 |
+
|
18 |
+
NoobAI-XL(v-prediction)をファインチューンし、SPOをマージしました。
|
19 |
+
|
20 |
+
日本語での導入手順はページ下部にあります。
|
21 |
+
|
22 |
+
## Requirements / 動作要件
|
23 |
+
- AUTOMATIC1111 WebUI on `dev` branch / devブランチ上のAUTOMATIC1111 WebUI
|
24 |
+
- Latest version of ComfyUI / 最新版のComfyUI
|
25 |
+
- ReForge on `dev_upstream_experimental` branch / `dev_upstream_experimental`ブランチ上のreForge
|
26 |
+
|
27 |
+
### Instruction for AUTOMATIC1111
|
28 |
+
1. Download the model
|
29 |
+
2. Switch branch to `dev`
|
30 |
+
3. Copy `configs/sd_xl_v.yaml` to `models/Stable-Diffusion/`
|
31 |
+
4. Rename it to the same as the model name
|
32 |
+
|
33 |
+
### Instruction for ReForge
|
34 |
+
1. Download the model
|
35 |
+
2. Switch branch to `dev_upstream_experimental`
|
36 |
+
3. Find “Advanced Model Sampling for Forge” at the bottom of the page
|
37 |
+
4. Enable “Enable Advanced Model Sampling”
|
38 |
+
5. Select `v_prediction` in Discrete Sampling Type
|
39 |
+
|
40 |
+
### Example Workflow for ComfyUI / ComfyUIサンプルワークフロー
|
41 |
+
Download it from [here](https://files.catbox.moe/v0isof.png)
|
42 |
+
|
43 |
+
## Prompt Guidelines / プロンプト記法
|
44 |
+
Almost same as the base model/ベースモデルとおおむね同じ
|
45 |
+
|
46 |
+
To improve the quality of background, add `simple background, transparent background` to Negative Prompt.
|
47 |
+
|
48 |
+
## Recommended Prompt / 推奨プロンプト
|
49 |
+
Positive: None/無し(Works good without `masterpiece, best quality` / `masterpiece, best quality`無しでおk)
|
50 |
+
|
51 |
+
Negative: `worst quality, low quality, bad quality, lowres, jpeg artifacts, unfinished, oldest, old, photoshop \(medium\), abstract`
|
52 |
+
|
53 |
+
## Recommended Settings / 推奨設定
|
54 |
+
Steps: 14-28
|
55 |
+
|
56 |
+
Sampler: DPM++ 2M(dpmpp_2m)
|
57 |
+
|
58 |
+
Scheduler: Simple
|
59 |
+
|
60 |
+
Guidance Scale: 4-9
|
61 |
+
|
62 |
+
### Hires.fix
|
63 |
+
|
64 |
+
Hires upscaler: 4x-UltraSharp or Latent(nearest-exact)
|
65 |
+
|
66 |
+
Denoising strength: 0.4-0.5(0.6 for latent)
|
67 |
+
|
68 |
+
## Training scripts:
|
69 |
+
[sd-scripts](https://github.com/kohya-ss/sd-scripts)
|
70 |
+
|
71 |
+
## Notice
|
72 |
+
This model is licensed under [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)
|
73 |
+
|
74 |
+
If you make modify this model, you must share both your changes and the original license.
|
75 |
+
|
76 |
+
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.
|
77 |
+
|
78 |
+
### AUTOMATIC1111の導入手順
|
79 |
+
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)。
|
80 |
+
2. モデルをダウンロードする。
|
81 |
+
3. `configs/sd_xl_v.yaml`を`models/Stable-Diffusion/`にコピーする
|
82 |
+
4. コピペしたファイルをモデル名と同名にする
|
83 |
+
|
84 |
+
### ReForgeの導入手順
|
85 |
+
1. `dev_upstream_experimental`ブランチに切り替える
|
86 |
+
2. モデルをダウンロードする。
|
87 |
+
3. WebUIのページ下部から“Advanced Model Sampling for Forge”を見つける
|
88 |
+
4. “Enable Advanced Model Sampling”を有効にする
|
89 |
+
5. Discrete Sampling Typeを`v_prediction`にする
|