|
--- |
|
license: other |
|
license_name: faipl-1.0-sd |
|
license_link: https://freedevproject.org/faipl-1.0-sd/ |
|
base_model: |
|
- Laxhar/sdxl_noob |
|
language: |
|
- en |
|
tags: |
|
- stable-diffusion |
|
- sdxl |
|
--- |
|
# Hikari Noob v-pred 0.5 |
|
|
|
 |
|
|
|
Civitai model page: https://civitai.com/models/938672 |
|
|
|
Fine-tuned NoobAI-XL(v-prediction) and merged SPO LoRA |
|
|
|
NoobAI-XL(v-prediction)をファインチューンし、SPOをマージしました。 |
|
|
|
日本語での導入手順はページ下部にあります。 |
|
|
|
## Features/特徴 |
|
- Improved stability and quality. |
|
- Works with samplers other than Euler. |
|
- Good results with only 10 steps (12 steps or more recommended) |
|
- Fixed a problem in which the quality of output was significantly degraded when the number of tokens exceeded 76. |
|
- 安定性と品質を改善 |
|
- わずか10ステップでよい結果を得られます(ただし12ステップ以上を推奨) |
|
- Zero Terminal SNRの代わりにNoise Offsetを使用することでEuler以外のサンプラーでも利用できるようにしました。 |
|
- トークン数が76を超えると出力の品質が著しく低下する問題を修正しました。 |
|
|
|
## Requirements / 動作要件 |
|
- AUTOMATIC1111 WebUI on `dev` branch / devブランチ上のAUTOMATIC1111 WebUI |
|
- Latest version of ComfyUI / 最新版のComfyUI |
|
- ReForge on `dev_upstream_experimental` branch / `dev_upstream_experimental`ブランチ上のreForge |
|
|
|
### Instruction for AUTOMATIC1111 |
|
1. Download the model |
|
2. Switch branch to `dev` |
|
3. Load the model |
|
|
|
### Instruction for reForge |
|
1. Download the model |
|
2. Switch branch to `dev_upstream_experimental` |
|
3. Find “Advanced Model Sampling for Forge” at the bottom of the page |
|
4. Enable “Enable Advanced Model Sampling” |
|
5. Select `v_prediction` in Discrete Sampling Type |
|
|
|
### Example Workflow for ComfyUI / ComfyUIサンプルワークフロー |
|
Download it from [here](https://files.catbox.moe/83e2wl.json) |
|
|
|
## Prompt Guidelines / プロンプト記法 |
|
Almost same as the base model/ベースモデルとおおむね同じ |
|
|
|
To improve the quality of background, add `simple background, transparent background` to Negative Prompt. |
|
|
|
## Recommended Prompt / 推奨プロンプト |
|
Positive: None/無し(Works good without `masterpiece, best quality` / `masterpiece, best quality`無しでおｋ) |
|
|
|
Negative: `worst quality, low quality, bad quality, lowres, jpeg artifacts, unfinished, photoshop \(medium\), abstract` or empty(または無し) |
|
|
|
|
|
## Recommended Settings / 推奨設定 |
|
Steps: 10-24 |
|
|
|
Sampler: DPM++ 2M(dpmpp_2m) |
|
|
|
Scheduler: Simple |
|
|
|
Guidance Scale: 3.5-7 |
|
|
|
### Hires.fix |
|
|
|
Hires upscaler: 4x-UltraSharp or Latent(nearest-exact) |
|
|
|
Denoising strength: 0.4-0.5(0.6 for latent) |
|
|
|
|
|
## Merge recipe(Weighted sum) |
|
I made 6 Illustrious-based models and merged them. |
|
|
|
- Stage 0: finetunes v-pred test model with AI-generated images |
|
- Stage 1: finetunes stage 0 model with 300 scenery images from Gelbooru |
|
|
|
- Stage 2: Finetune and merge(see below) |
|
|
|
*A-F,sd15: finetuned stage1(ReLoRA) |
|
|
|
- A * 0.6 + B * 0.4 = tmp1 |
|
- tmp1 * 0.6 + C * 0.4 = tmp2 |
|
- tmp2 * 0.7 + F * 0.3 = tmp3 |
|
- tmp3 * 0.7 + E * 0.3 = tmp4 |
|
- tmp4 * 0.5 + D * 0.5 = tmp5 |
|
- tmp5 * 0.65 + sd15 * 0.35 = tmp6 |
|
- tmp6 + SPO LoRA = Result |
|
|
|
## Training scripts: |
|
[sd-scripts](https://github.com/kohya-ss/sd-scripts) |
|
|
|
## Notice |
|
This model is licensed under [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/) |
|
|
|
If you make modify this model, you must share both your changes and the original license. |
|
|
|
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. |
|
|
|
### AUTOMATIC1111の導入手順 |
|
1. モデルをダウンロードする。 |
|
2. 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)。 |
|
3. モデルを読み込む。 |
|
|
|
### ReForgeの導入手順 |
|
1. `dev_upstream_experimental`ブランチに切り替える |
|
2. モデルをダウンロードする。 |
|
3. WebUIのページ下部から“Advanced Model Sampling for Forge”を見つける |
|
4. “Enable Advanced Model Sampling”を有効にする |
|
5. Discrete Sampling Typeを`v_prediction`にする |
