CivArchive
    [Deprecated]Illumina-NoobVpd - 0.5test
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    Hugging Face Repo(v0.5test): https://huggingface.co/RedRayz/illumina-noob-vpd

    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モデルを複数作成しマージしたものです。

    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

    日本語の導入手順はHugging Faceのリポジトリをご覧ください。

    Instruction for AUTOMATIC1111

    1. Download the model

    2. Switch branch to dev

    3. Copy configs/sd_xl_v.yaml to models/Stable-Diffusion/

    4. Rename it to the same as the model name

    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

    Download it from here

    To improve the quality of background, add "simple background, transparent background" to Negative Prompt.

    背景の品質を向上させるには、"simple background, transparent background"をネガティブプロンプトに追加してください。

    Positive: None(works good without "masterpiece, best quality")

    Negative: "worst quality, low quality, bad quality, lowres, jpeg artifacts, unfinished, oldest, old, photoshop \(medium\), abstract"

    Tips: Leaving Negative Prompt empty will increase the diversity of styles(less 'masterpiece').

    ヒント: ネガティブプロンプトを空にしておくと画風の多様性が高くなります(マスピ感を軽減)。

    Steps: 14-28

    Sampler: DPM++ 2M

    Scheduler: Simple

    Guidance Scale: 4-9

    Upscaler: 4x-UltraSharp(or ESRGAN-based model), Latent(nearest-exact)

    Denoising strength: 0.4-0.5(0.6 for latent)

    Training information

    Please visit the Hugging Face repository

    Training script

    sd-scripts

    Notice/おしらせ:

    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.

    このモデルはFair AI Public License 1.0-SDでライセンスされています。

    このモデルを改変する場合、変更点および元のライセンスを明記する必要があります。

    モデルのソースコード/ウェイトや使用法などを閲覧できないクローズソースのファインチューン/マージモデルの収益化は禁止されています。

    Description

    Based on v-pred test version(NOT 0.5 v-pred)

    FAQ

    Checkpoint
    SDXL 1.0

    Details

    Downloads
    242
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/4/2024
    Updated
    4/22/2026
    Deleted
    -

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.