RedRayz/hikari_noob_0.6.5

DO NOT RE-UPLOAD THIS MODEL

Please make a pull request to add a converted format version.

Hikari Noob v-pred 0.6.5

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

Fine-tuned NoobAI-XL(ν-prediction) and merged SPO LoRA

NoobAI-XL(ν-prediction)をファインチューンし、SPOをマージしました。

Features/特徴

• Improved stability and quality.
• Fixed a problem in which the quality of output was significantly degraded when the number of tokens exceeded 76.
• 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 0.6), so it has the equivalent knowledge. You can generate characters that have appeared by August 2024.
• 安定性と品質を改善
• 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。
• 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 0.6)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。2024年8月までに登場したキャラクターを生成できます。

About v0.6.5

• Enabled Zero Terminal SNR

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

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, Leaving negative empty will break the output! Use _ instead.

Recommended Settings / 推奨設定

Steps: 12-24

Scheduler: Simple

Guidance Scale: 2-7

Compatible Samplers

• Euler(fast, stable)
• Euler a(fast)
• DPM++ 2M(high quality, fast, unstable)
• DPM++ SDE(high quality, slow)
• DPM++ 2s a(high quality, slow)
• DPM adaptive(extremely slow)

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 0.6 and merge(see below) *A-I: noobai(v-pred)-based custom checkpoint
• 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 + G * 0.35 = tmp6
• Make H,I from tmp6
• tmp6 * 0.75 + H * 0.25 = tmp7
• tmp7 * 0.75 + I * 0.25 = tmp8
• tmp8 + SPO LoRA * 1 + sdxl-flat * -0.25 + sdxl-boldline * -1 = tmp9
• Adjust tmp9(0.2,0.2,0.2,0.1,0,0,0,0) = 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.

Do not reupload this model.