CivArchive
    MyTale - v3
    NSFW
    Preview 3405099
    Preview 3405083
    Preview 3405100
    Preview 3405097
    Preview 3405080
    Preview 3405098
    Preview 3405093
    Preview 3405092
    Preview 3405085
    Preview 3405087
    Preview 3405094
    Preview 3405095
    Preview 3405089

    Hi there, I played around a lot with stable diffusion marges those days, and from this i decided to make one for me and my tastes.

    This model uses Anylora as a base, then it was mixed with multiple anime base models (sorry i can't give you more details because i don't know them my self XD) till i ended up with a model that matched my tastes and that was "different" from other models i've seen.

    What is this model objective?

    Well the goal was to achieve a good model that excels in portraits, but that can easily be used with good results in any scenario.

    It works best with images of girls, but it can produce boys, landscapes, and even NSFW images.

    Suggestions:

    I've tested quite a while (till my gpu begged for a break) and i have to say that it can give good results in both clip skip 1 and clipskip 2.

    The samplers i tested were Euler A, DPM++ 2S a, DPM++ SDE Karras and those have produced good results, but feel free to test. (If you want a more precise setting you can check the bottom part of this page).

    The LoRa compatibility is quite good, i tested them a lot, and it perform goodly enoght even with my "failed ones".

    The In-Paint is quite good, especially for female faces, but you rarely need to do it if you use hig.res.fix.

    [Attention]: HighRes.Fix is not mandatory, but it is highly recomended!!!

    As upscaler you can use eighter: "r-esrgan 4x+ anime 6b" or "ultrasharp anime".

    Suggested Embeddings

    EasyNegativeV2

    BadHand-5

    aid210

    an10

    negativefeet

    deepnegative

    verybadnegativeimages

    Examples of settings:

    Sampler: Euler A
    Steps: 40 - 60
    Cfg: 7
    Image resolution: 512x512 ; 512x768; 768x512   (it works even with higher ones but there's really no point in sterssing the hardware when you can upscale later)
    vae: vae-ft-mse-840000-ema-pruned_fp16
    
    ------------------------------------------------------------------------------
    
    Upscaler: r-esrgan 4x+ anime 6b
    steps: 10-20
    denoise: 0.1 - 0.4
    
    Sampler: DPM++ SDE Karras
    Steps: 30 - 40  (it might work with higher ones, but i didn't test those)
    Cfg: 7
    Image resolution: 512x512 ; 512x768; 768x512   (it works even with higher ones but there's really no point in sterssing the hardware when you can upscale later)
    vae: vae-ft-mse-840000-ema-pruned_fp16
    
    ------------------------------------------------------------------------------
    
    Upscaler: r-esrgan 4x+ anime 6b
    steps: 10-20
    denoise: 0.1 - 0.4

    Description

    I've worked on this for a while, and i wanted to tweek it a little more before release but, considering how somepeople have some issue with v2, i've decided to release v3 earlier than planned.

    This Version is the Stable one, it is not planned to receive a major update in the short period.

    It has the strenght of the v1 and the v2, but it's less dependant on upscale to achieve awesome results (note: the sample images were still upscaled just cause i like them more, but as you can see they weren't really cherry picked or inpainted at all. Controlnet was not used in the generation of those images so they could've been much better).

    It is suggested the used of negative embeddings such as EasyNegative, DeepNegative, Verybadimages and/or AmoreNegative.

    This version works quite well in clip skip 2 but it can work aswell in clip skip 1, test the output and check what it matches your tastes more (i for example like clip skip2 more).

    The suggested Setting in the model details fully apply to this version.

    [Important]: Highres.Fix is still recomended (as for the upscaling using "RealESRGAN_x4plus_anime_6B")

    [FootNote]

    If you don't like prompt engeneering this version is the recomended one (rather than the v1 or v2).

    FAQ

    Checkpoint
    SD 1.5

    Details

    Downloads
    648
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/5/2023
    Updated
    4/23/2026
    Deleted
    -

    Files

    mytale_v3.yaml

    Mirrors

    CivitAI (87 mirrors)

    mytale_v3.safetensors

    Mirrors

    CivitAI (1 mirrors)
    Other Platforms (TensorArt, SeaArt, etc.) (1 mirrors)

    Available On (1 platform)

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