← 返回排行榜

[PVC Style Model]Movable figure model 微调模型

MIAOKA · · Anima

Anima 的社区微调版,作者 MIAOKA。

特点

适用范围

关键参数

所属底模
Anima
累计下载
71.4k
发布
版本数
2

本机部署建议(RTX 5060 Ti 16GB)

16GB 结论
体积与 Anima 原版同档;16GB 上按底模的量化策略走即可。

使用建议

作者原文摘录

An update for the "Movable Figure Model Anima 2.9B" has been released. This model is based on Anima 2.9B please refer to the "About this version" section for detailed image generation parameters. Movable Figure Model_CKN_EPS_V1.1 A Release Announcement We are officially releasing Movable Figure Model_CKN_EPS_V1.1 A! As the latest iteration of the Movable Figure Model series, this update marks a new step towards the CKN architecture. It's important to note that V1.1 will be released in two versions. This initial release is "Version A" (focusing on current basic performance and specific style enhancements), while "Version B," serving as a supplement and exploration, is currently under intensi…

作者例图请在 Civitai 模型页 查看(站外,含成人内容风险,不做内嵌)。

官方 ComfyUI 工作流

下载 JSON 后拖进 ComfyUI 窗口即可载入;缺节点通常是 ComfyUI 版本太旧。

官方链接

下载 / 安装

文件级链接点一下就直接下载(HF 会 302 到 CDN);每条下面标了精度档位与最低显存,命令行口令点右上角「复制」。

国内镜像(推荐)

civitai.work 镜像站(第三方)
页面与官网同源;下载同样需要登录

官方直连

Civitai 模型页(登录后点 Download)
浏览器已登录即可一键下载,最省事
直链 · models/3402701
需要登录态或 Token,未登录会返回 401
命令行下载(需 API Token:civitai.com/user/account)
curl -L -o "PVCStyleModelMovable_anima29B10.safetensors" "https://civitai.com/api/download/models/3402701?token=<你的TOKEN>"
多线程断点续传(aria2)
aria2c -x8 -s8 -c -o "PVCStyleModelMovable_anima29B10.safetensors" "https://civitai.com/api/download/models/3402701?token=<你的TOKEN>"

显存是「最低可跑」的估算:ComfyUI 会分时加载权重与文本编码器,所以最低显存≈权重体积再上一档;实际还要给激活值留余量,视频模型另受时长与分辨率影响。

放到哪:底模 → ComfyUI/models/diffusion_models;LoRA / 微调 → models/loras 或 models/checkpoints;文本编码器 → models/text_encoders;VAE → models/vae。Comfy-Org 的仓已按这套目录结构打包,--local-dir ComfyUI\models 即可直接落位。