Hikari Noob v-pred 1.1.0

Civitai model page: https://civitai.com/models/938672?modelVersionId=1324491

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。絵柄はややばらつきがあり、「典型的AIイラスト」感を抑えています。

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

Features/特徴

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.
安定性と品質を改善
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。

About 1.1.0

Adjust style
Better stability?

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

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

(日本語)

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)
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

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, photoshop \(medium\), abstract or empty

Recommended Settings / 推奨設定

Steps: 12-24

Scheduler: Simple or SGM Uniform

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

Recommended Samplers

DPM++ 2M
DPM++ 2M SDE
DPM++ 3M SDE
Euler/Euler a other samplers will not work properly.

Hires.fix

Hires upscaler: 4x-UltraSharp or Latent(nearest-exact)

Denoising strength: 0.4-0.5(0.65-0.7 for latent)

Merge recipe(Weighted sum)

Stage 1: Finetune Noob v-pred 1.0 and merge(see below) *A-N: Fine-tuned NoobAI
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 * 0.6 + D * 0.4 = tmp5
tmp5 * 0.7 + G * 0.3 = tmp6
Make H,I,J,K from tmp6
tmp6 * 0.75 + H * 0.25 = tmp7
tmp7 * 0.7 + I * 0.3 = tmp8
tmp8 * 0.7 + J * 0.3 = tmp9
tmp9 * 0.9 + K * 0.1 = tmp10
Make L from tmp10
tmp10 * 0.85 + L * 0.15 = tmp11
Make M from tmp11
tmp11 * 0.8 + M * 0.2 = tmp12
Make N from tmp12
tmp12 * 0.8 + N * 0.2 = tmp13
tmp13 + SPO LoRA * 1 + sdxl-flat * -0.25 + sdxl-boldline * -1 = tmp14
Adjust tmp14(0.2,0.2,0.2,0.05,0,0,0,0) = Result

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.

RedRayz
/

hikari_noob_v-pred_1.1.0