CivArchive
    MexxL_LCM2 - v1.0
    Preview 4346797
    Preview 4346808
    Preview 4346791
    Preview 4072901
    Preview 4072910
    Preview 4072902
    Preview 4072905
    Preview 4072906
    Preview 4072934
    Preview 4072943
    Preview 4346964
    Preview 4346966
    Preview 4346962
    Preview 4346963
    Preview 4346965
    Preview 4346968
    Preview 4346967
    Preview 4346972
    Preview 4346969
    Preview 4346971

    I found a new AI tool Shakker, a best image to image tool. You can try it via https://www.shakker.ai

    SDXL 的 LCM2 的基础模型,做了一些调整和优化,所以不适用LCM采样器,对SDE类别的采样器十分友好。


    如果您不阅读繁琐的文档,那么这里推荐的配置如下:

    采样器:DPM++ SDE Karras

    CFG:1.5-2.5

    步数:5


    采样器推荐

    针对SDE采样器比较友好,推荐采样器如下

    1. DPM++ SDE Karras - 速度慢,细节更完美(5步+)

    2. DPM++ 2M SDE Karras - 速度快(5步+)

    3. DPM++ SDE - 适合高步数(8步+),速度慢,细节更完美


    CFG 推荐

    CFG通常设置为1即可,可以调整为1-3,值越大,收拢速度越快,也就是可以使用更少的步数完成图片的生成。


    测试用例

    Prompt: (Well-bred's works:1.13),a beautiful girl, 24yo, skinny, pretty, [k-pop:detailed eyes, detailed beautiful face:0.5],

    Negative Prompt: ng_deepnegative_v1_75t,negative_hand,disfigured,ugly,deformed,worst quality,low quality,extra limbs,extra legs,extra arms,deformed hands,deformed anatomy,umbrella,

    采样:DPM++ 2M SDE Karras 或者 DPM++ SDE Karras

    步骤:5+

    尺寸:768 x 1024 以上


    采样器测试

    以5步为例,不同采样器效果如下

    以10步为例,不同采样器效果如下

    以20步为例,不同采样器效果如下


    DPM++ 2M SDE Karras 步数测试

    DPM++ 2M SDE Karras比较适合快速抽卡,从1步到8步的效果如下

    第4步就形成了可用的图像,随着步数的增加,细节逐渐完善。

    更多测试报告:https://www.yuque.com/mengxiangyuan-7fhri/eo7oa2/gtifyimxamueeixg?singleDoc# 《SDXL-LCM采样器测试报告》


    My Github:

    https://github.com/SoftMeng/ComfyUI_Mexx_Styler

    https://github.com/SoftMeng/ComfyUI_Mexx_Poster

    https://github.com/SoftMeng/ComfyUI_Mexx_Image_Mask

    https://github.com/SoftMeng/stable-diffusion-prompt-pai

    https://github.com/SoftMeng/Fooocus-zh

    Or My LibLib:

    https://www.liblib.art/userpage/0f37258e861044879b8728309c0ac3b0/publish

    Description

    LCM的基础模型,我是用以下参数进行测试的,有不错的效果

    Prompt: a beautiful girl,

    Negative Prompt: ng_deepnegative_v1_75t,negative_hand,disfigured,ugly,deformed,worst quality,low quality,extra limbs,extra legs,extra arms,deformed hands,deformed anatomy,umbrella,

    采样:DPM++ SDE (效果最好) 或者 DPM++ 2M Karras (速度快些)

    步骤:5

    尺寸:768 x 1024 以上

    FAQ

    Comments (10)

    Ng_SowhaTDec 1, 2023· 1 reaction
    CivitAI

    等資源多點再玩LCM 現在我LCM不知道哪裡出問題了 會報錯 只好等以後有更簡潔的教程再玩

    LCM比男人還快

    ehnlo41045889Dec 2, 2023
    CivitAI

    lcm是不是不能加其他lora使用
    我不加10秒出圖
    加了要1分鐘

    23562335108Dec 14, 2023
    CivitAI

    good

    softMeng
    Author
    Dec 22, 2023· 1 reaction
    CivitAI

    DPM++ SDE Karras is Very Good

    SuzanneDec 22, 2023· 1 reaction
    CivitAI

    Hi, everyone, 🖖

    Does anyone know the differences between the "basic" SDXL version and the "LCM" "distilled" version and which are compatible with all UIs, A1111 and Fooocus?

    Thanks

    SuzanneDec 23, 2023
    CivitAI

    🖖 How long do your renderings take?

    I saw a tutorial on the internet that said rendering didn't take more than 5 seconds, but it was with ComfyUI.

    I've done a few tests with Fooocus and it takes 1 minute to render and with the other models I never go over 30 seconds.

    Do you have any ideas?

    aiisoft360Dec 28, 2023
    CivitAI

    一个字:屌

    softMeng
    Author
    Jan 11, 2024· 2 reactions
    CivitAI

    感谢每个人的点赞,谢谢每个人的支持,万胜!

    cao888888Jan 14, 2024
    CivitAI

    女模特的眼睛可以优化一下下,总有点像斗鸡眼的角度,大小眼也比较明显。

    chelseynelson2008725Feb 3, 2024
    CivitAI

    I'm bootstrapping this model, why do I get an error

    size mismatch for model.diffusion_model.output_blocks.8.0.out_layers.3.bias: copying a param with shape torch.Size([320]) from checkpoint, the shape in current model is torch.Size([640]).

    Checkpoint
    SDXL 1.0 LCM

    Details

    Downloads
    1,439
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/1/2026
    Deleted
    4/24/2025

    Files

    mexxlLCM2_v10.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)