CivArchive
    [NoobAI-XL EPS 1.1]"cogecha" style|"焦糖"风格 - v1.0
    NSFW
    Preview 55900628

    请务必在NoobAI-XL (NAI-XL) EPS系列模型上使用该模型! 我并没有在其他种类的模型上使用测试过该Lora的使用效果!

    使用底模为:

    NoobAI-XL (NAI-XL) - Epsilon-pred 1.1-Version | Stable Diffusion XL Checkpoint | Civitai

    在公共互联网发布由该模型生成的图片时,请标注模型来源!

    训练数据来源:Cogecha | Danbooru (donmai.us)


    Please be sure to use this model on the NoobAI-XL (NAI-XL) EPSseries models! I haven't tested the performance of this Lora on other types of models!

    Base model:

    Using the base model:

    NoobAI-XL (NAI-XL) - Epsilon-pred 1.1-Version | Stable Diffusion XL Checkpoint | Civitai

    When publishing images generated by this model on the public internet, please indicate the source of the model!

    Training data source:Cogecha | Danbooru (donmai.us)

    Description

    FAQ

    Comments (13)

    BIG_AFeb 5, 2025· 1 reaction
    CivitAI

    就不在nooB用,就不用,气死你~

    BeiWay1145
    Author
    Feb 5, 2025

    不管怎么说,感谢支持[doge]

    BIG_AFeb 5, 2025· 1 reaction

    @BeiWay1145 我偶尔会突然发病,请见谅

    BeiWay1145
    Author
    Feb 5, 2025

    @BIG_A 没事的,理解。owo

    yezixun66178Jul 23, 2025

    怎么说,其他模型能用吗

    BIG_AJul 23, 2025

    yezixun66178 应该不能,就算可以运行,效果也不好,还是老实在noob上用,我这条评论完全就是闲着没事犯贱而已。

    iamcakeFeb 5, 2025· 1 reaction
    CivitAI

    为什么我下载下来的是另一个画师的lora画风,大佬求解

    BeiWay1145
    Author
    Feb 5, 2025

    蛤?我瞅一眼

    BeiWay1145
    Author
    Feb 5, 2025

    你可以发一下你使用的checkpoint模型还有正面tag吗?我这边发现我并没有上传错误的模型。

    BIG_AFeb 5, 2025

    必须用NOOB模型,其他模型不行,宝贝

    iamcakeFeb 8, 2025· 1 reaction

    @BeiWay1145 

    Filename:dz_nbe_cogecha-00500.safetensors

    文件大小:File size:163MB

    Hash:ff841d091d10

    最后修改日期:Modified:2025-02-08 07:01

    Output name:dz_nbe_quan_(kurisu_tina)

    模型:Model:NoobAI-XL (NAI-XL)_Eps-pred 110%.safetensors

    Kohya 模块类型:Kohya module:networks.lora

    训练日期:Date trained:2025-02-01 17:02

    分辨率:Resolution:1024x1024

    数据集大小Dataset size:24

    这是用loeme theme读取出来的lora参数,然后触发词也是quan这个画师的;我贴上了图,用的模型也是noob系列的,加上这个lora之后是向quan的画风贴近了

    BeiWay1145
    Author
    Feb 8, 2025

    @iamcake 我刚才查看了一下我这边的本地备份,很不幸,这个实际上也是quan的lora。
    大概是因为我在训练quan的lora时候误使焦糖画风的lora被错误替换了罢。
    有点可惜(
    不过训练集的备份我应该保存下来了,我等会找一下。
    这个画风lora可能会在未来的某一天里重新训练并发布吧。
    时间应该不会很长(大概?

    BeiWay1145
    Author
    Feb 9, 2025

    @iamcake 新版本已发布 因为改进了训练方法 比之前的版本表现更好一些(虽然用的还是之前的训练集)

    LORA
    Illustrious

    Looks like we don't have an active mirror for this file right now.

    CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.

    Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.

    Details

    Downloads
    81
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    2/5/2025
    Updated
    5/21/2026
    Deleted
    8/7/2025
    Trigger Words:
    artist:cogecha

    Files

    dz_nbe_cogecha-000500.safetensors

    Mirrors

    Available On (1 platform)

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