CivArchive
    Shadow97's Particle - M3A1
    NSFW
    Preview 742811
    Preview 742813
    Preview 742814
    Preview 742815
    Preview 742812
    Preview 742817
    Preview 742816
    Preview 742818
    Preview 742819
    Preview 742820
    Preview 742822
    Preview 742821
    Preview 742823
    Preview 742824
    Preview 742825
    Preview 742826
    Preview 742828
    Preview 742829
    Preview 742827
    Preview 742830

    This is a rather old model of mine, so it might be faulty in some aspects. Most notably, it sometimes produces nonsensical faces and creates textures where they shouldn't be, but you should be fine as long as you use recommended settings.

    Sampler: DPM++ 2M Karras, DPM++ SDE Karras

    Steps: 20+

    CFG Scale: Anywhere between 4 to 11, beyond that I did not test, but I doubt you'd be using values outside of that bracket anyway. Lower scale values seem to be more "creative" at the cost of producing more muted colors. Also, higher CFG scale values tend to produce aforementioned errors more often (for instance, on Euler a with 20 steps and no hires.fix)

    Hires.fix: on, upscaler either any of the Latents or R-ESRGAN 4x of your taste. Latent is more creative, R-ESRGAN is less prone to nonsense generations. Use denoise strength in the range of 0.55 to 0.75 for Latent and 0.3 to 0.75 for R-ESRGAN.

    Clip Skip: 1 or 2, the effect is similar to CFG Scale with 1 being more creative and 2 having deeper contrast and more popping colors (all example images made with Clip Skip 2).

    VAE: the one from the base SD 1.5 model. I didn't bake it in just in case you want to use something else with the model.

    Description

    Merged in some Hassaku to improve overall body composition and hentai capabilities (still not transcending Stable Diffusion's innate limitations, but yeah):

    https://civitai.com/models/2583/hassaku-hentai-model

    FAQ

    Comments (5)

    MUYIEGMay 10, 2023· 2 reactions
    CivitAI

    It looks great !, Do you have any recommended VAE then?~

    shadow97
    Author
    May 10, 2023

    My favorite VAE, and the one I use with most models, is the standard SD 1.5 VAE (I don't remember its exact name, but you will probably have no problem googling it up). I also like kl-f8-anime2 and blessed2 VAEs.

    MUYIEGMay 10, 2023

    @shadow97 Understood, thank you very much (I also like kl-f8-anime2)

    bg0051May 10, 2023
    CivitAI

    is this model w512*h768 image only? w768* h512 create bad image my generate result...

    shadow97
    Author
    May 10, 2023· 1 reaction

    Quite a lot of models that I tried have this problem. To be more precise, prompts that work well with portrait resolutions don't work that well on landscape ones, so I'd suggest starting with a more simple prompt, then developing it into what you actually want to see, then notice where the problem arises and find ways to fix it in the prompt. Unfortunately, I can't give any more specific advice as I have no access to your generation setup.

    Also, all pictures in the examples are 720 by 1280, not 512 by 768 xD

    Checkpoint
    SD 1.5

    Details

    Downloads
    837
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/9/2023
    Updated
    5/11/2026
    Deleted
    -

    Files

    shadow97sParticle_m3a1.safetensors

    Mirrors

    Available On (1 platform)

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