RedRayz/hikari_noob_v-pred_1.2.1

Hikari Noob v-pred 1.2.1

Civitai model page: https://civitai.com/models/938672

NoobAI-XL(v-pred 1.0) based anime model with human artist style

Fine-tuned NoobAI-XL(v-prediction) without merging another base models, and merged SPO(Step-aware Preference Optimization) LoRA

他所のベースモデルを混ぜずに調整し、SPO LoRAをマージしたNoobAI-XL(v-prediction)

NoobAI-XL(v-prediction版)に特定画風を学習させたcheckpointを複数作成しマージしたものです。「典型的AIイラスト」感を抑えつつ、鮮やかで非常に美しいイラストを生成します。

This model does not have the "AI Masterpiece" style.

Features/特徴

• Greatly improved stability and quality.
• The base style is not strong and can be restyled by prompts or LoRAs.
• This model does not include any base model other than NoobAI (v-prediction), so it has the equivalent knowledge.
• True v-prediction model with Zero Terminal SNR
• 安定性と品質を大幅に改善
• 素の画風は強くないので、プロンプトやLoRAによる画風変更ができます。
• このモデルはNoobAI(v-prediction版)以外のベースモデルを一切含まず、それと同等の知識があります。
• 真のv-prediction + Zero Terminal SNRなモデル

About 1.2.1

• Greatly improved output quality
• Fixed some issues

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
• Latest version of Forge or reForge / 最新版のForgeまたはreForge

Instruction for AUTOMATIC1111 / AUTOMATIC1111の導入手順

1. Switch branch to dev (Run this command in the root directory of the webui: git checkout -b dev origin/dev or use Github Desktop)
2. Use the model as usual!

(日本語)

1. devブランチに切り替えます(次のコマンドをwebui直下で実行します: git checkout -b dev origin/dev またはGithub Desktopを使う)
2. 通常通りモデルを使用します。

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

Positive prompt: Works good without quality tags / 品質タグ無しでおｋ

Negative prompt: Leave it empty(old and worst quality have no effects)

Recommended Settings / 推奨設定

Steps: 14-24

Guidance Scale: 2-5(best value is 4)

Recommended Samplers

• DPM++ 2M
• DPM++ 2M SDE
• DPM++ 2M SDE Heun

other samplers are not tested/good.

Recommended Noise Schedulers

• Simple
• SGM Uniform

Hires.fix

Hires upscaler: 4x-UltraSharp or Lanczos

Denoising strength: 0.4-0.5

Merge recipe(Weighted sum)

Merge the quality improvement LoRA to v1.1.0(dataset images from v1.1.0 output)

Training scripts:

sd-scripts

Notice

This model is licensed under Fair AI Public License 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.