CivArchive
    Anima | 徐尤点 画风 | XuYouDian Style - V1.0
    NSFW
    Preview 128142351
    Preview 128142352
    Preview 128142358
    Preview 128142355
    Preview 128142360
    Preview 128142363
    Preview 128142365
    Preview 128142437
    Preview 128142435
    Preview 128142441
    Preview 128142440
    Preview 128142452
    Preview 128142451
    Preview 128142457
    Preview 128142459
    Preview 128142471
    Preview 128144365
    Preview 128141378
    Preview 128141379
    Preview 128141386

    Anima | XuYouDian Style

    来点评论喵,来点返图谢谢喵

    Please leave a comment and share some photos, thank you! This will motivate me to keep updating!

    Base Model : Anima Base-v1

    Version Introduction

    • Version 1 base on P3

    • Version 2 base on Base-v1

    Generation settings

    • Works at resolutions between 512^2 and 1536^2 pixels.

    • 30-50 steps, CFG 4-6.

    • A variety of samplers work. Some of my favorites:

      • er_sde: neutral style, flat colors, sharp lines. I use this as a reasonable default.

      • euler_a: Softer, thinner lines. Can sometimes tend towards a 2.5D look. CFG can be pushed a bit higher than other samplers without burning the image.

      • dpmpp_2m_sde_gpu: similar in style to er_sde but can produce more variety and be more "creative". Depending on the prompt it can get too wild sometimes.

    • If going for a more realistic / painterly look, the beta57 scheduler (ComfyUI RES4LYF custom node pack) can help make better textures, since it puts more emphasis on low-noise timesteps.

    Quoted from the official description; you may also refer to the parameter settings shown in the example image

    I do not prohibit merging using my model, but I hope to follow open source conventions and make the recipe public.

    Description

    不推荐使用放大

    FAQ

    LORA
    Anima

    Details

    Downloads
    314
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/21/2026
    Updated
    9/1/2026
    Deleted
    -

    Files

    Anima_Style_XuYouDian.safetensors

    Mirrors