找回密码
 立即注册

QQ登录

只需一步,快速开始

查看: 41|回复: 0

[CP0139][Checkpoint][SD 1.5][AAM_anylora_animemix.safetensors][AAM - AnyLoRA Anime Mix - Anime Screencap Style Model][二次元][动漫截图风格][高质量][角色训练][适合LoRA]

[复制链接]
  • TA的每日心情
    慵懒
    10 小时前
  • 签到天数: 51 天

    [LV.5]常住居民I

    1349

    主题

    56

    回帖

    7053

    积分

    管理员

    积分
    7053
    发表于 2026-9-30 16:09:11 | 显示全部楼层 |阅读模式
    📦 模型信息

    编号CP0139
    模型文件AAM_anylora_animemix.safetensors
    模型名称AAM - AnyLoRA Anime Mix - Anime Screencap Style Model
    模型类型Checkpoint
    风格分类二次元
    模型标签动漫截图风格|高质量|角色训练|适合LoRA
    基础模型SD 1.5
    版本v1
    文件大小3.22 GB
    文件格式SafeTensor / fp16
    发布时间2023-06-05


    📝 模型详细介绍

    AnyLoRA Anime Mix (AAM)Anime Screencap Style ModelDo you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕. A ❤️, a kind comment or a review is greatly appreciated.Please check out AAM XL tooPurpose of this modelMake amazing anime style artworks on its own.Train character loras where the dataset is mostly made of anime screencaps, allowing less anime style transfer and less overfitting.Use anime styles if the lora is "weak" and doesn't give enough flat coloring.It's also pretty good at generating hentai stuff.Suggested settingsSet the ETA Noise Seed Delta (ENSD) to 31337Set CLIP Skip to 2DISABLE face restore. It's terrible, never use itUse negative prompts and embeddings that don't ruin the styleUse AnimeVideo or Foolhardy as upscalers. If you know what to do, Latent makes an interesting effect (see the first example and the Miku one)(optional to reproduce some results) Set "Do not make DPM++ SDE deterministic across different batch sizes." Only my old images use that. (this setting is not actually good, so I'm gonna disable it, but might be the reason some results are different)LCM versionUse it with 5-15 steps, ~2 cfg. LCM VERSION WORKS ONLY WITH LCM SAMPLER (to get it on Auto1111 you currently need a plugin).Being a distilled model it has lower quality compared to the base one. However it's MUCH faster and perfect for video and real time applications.Brief historyChatting on Discord, I noticed my Mushoku Tensei style LoRA, while trained on AnyLoRA, was performing a bit better on CyberAlchemist's AnimeMix base model. I read on his HF that the model was a supermerge of AnythingElse, his AnimeMix lora and various other style loras. Since AnimeMix was already including many of my old anime style loras, I wanted to experiment and try to make a model that could maximize the result of my Mushoku Tensei style, going beyond what AnyLoRA and AnimeMix could do.After testing many different versions, adjusting the settings and receiving feedback from the Discord channel, I ended up with a version that works very well on anime loras trained on AnyLoRA (base). Especially my Mushoku Tensei one which felt very weak on AnyLoRA.I don't advise using this for anime style training (limit to generation after training it on AnyLoRA or NAI), but it might actually be fairly good for character loras where your dataset is made mostly of anime screencaps. It should technically reduce the anime style impact making the character lora less overfitted. I'll definitely experiment with it in the following weeks.

    🏷️ 模型特点 / 标签

    anime、woman、game character、sexy、female、landscapes、base model、video game、anime screencap、girls、portraits

    🖼️ 模型预览(10张)



    🔗 原文链接

    https://civitai.com/models/84586

    📥 下载地址

    游客,如果您要查看本帖隐藏内容请回复



    您需要登录后才可以回帖 登录 | 立即注册

    本版积分规则

    Archiver|小黑屋|SD创意工坊 ( 京ICP备16065101号 )|网站地图

    GMT+8, 2026-11-22 21:25 , Processed in 0.029942 second(s), 21 queries .

    Powered by Discuz! X3.5

    Copyright © 2001-2020, Tencent Cloud.

    快速回复 返回顶部 返回列表