CivArchive
    Async's MIX XL - v3.0
    NSFW
    Preview 7063956
    Preview 7063949
    Preview 7063948
    Preview 7063950
    Preview 7063954
    Preview 7063947
    Preview 7063959
    Preview 7063953
    Preview 7063962

    Async's MIX XL merge checkpoint model.

    This model focuses on producing anime images.

    sdxl_vae is vaked in.

    Trouble shooting

    If you are using webui and the image is black or has a strange tint.

    In the settings, turn off "Enable Emphasis" from the StableDiffusion section. In that case, the result will be different from the sample image above.

    Image results are different from the sample image above.

    The version of WebUI when I created my sample images was 1.7.0, and I did not include any extensions. And I used Negative Embedding such as an14 or an12 to create it, so please download it once and place it in the designated Embedding folder to regenerate it.

    an14,an12 Negative Embedding

    Async's Negative - v14 | Stable Diffusion Embedding | Civitai

    settings

    clip skip : 2

    ENSD:0

    quality prompt

    (Depth of field hdr 8k 4k wallpaper cinematic angle, cinematic lighting,:1.5) (masterpiece, best quality:2.0), (Depth of field hdr 8k 4k wallpaper cinematic angle, cinematic lighting,:1.5) (masterpiece, best quality:2.0)

    negative prompt

    n12_light (an12:1.2) (kneeling  lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,:1.5),, an12_light an12 ( lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,:1.5)

    example

    
    anime,1girl,(Depth of field hdr 8k 4k wallpaper cinematic angle, cinematic lighting,:1.5) (masterpiece, best quality:2.0), (Depth of field hdr 8k 4k wallpaper cinematic angle, cinematic lighting,:1.5) (masterpiece, best quality:2.0)
    Negative prompt: an12_light (an12:1.2) (kneeling  lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,:1.5),, an12_light an12 ( lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,:1.5)
    Steps: 45, RNG: CPU, Size: 896x1152, Seed: 2079619126, Model: Async's MIX XL, Version: v1.7.0, Sampler: DPM++ 2M Karras, CFG scale: 7.5, Clip skip: 2, Model hash: 9abe366cab, Hires steps: 45, Hires upscale: 1.25, Hires upscaler: Latent (nearest-exact), Denoising strength: 0.6

    Description

    FAQ

    Comments (6)

    KainKarnageFeb 24, 2024
    CivitAI

    Version 3 detail card shows base model being SD 1.5

    asyncforai414
    Author
    Feb 24, 2024· 1 reaction

    Thanks. Fixed.

    asukaylink663Mar 7, 2024· 2 reactions
    CivitAI

    incredible it also works as a turbo model

    SamariApr 15, 2024· 1 reaction
    CivitAI

    Async's MIX XL is among the top-tier models based on AnimagineXL. I eagerly await the release of the new version compatible with AnimagineXL ver3.1.

    asyncforai414
    Author
    May 11, 2024

    Model updated.

    SamariMay 13, 2024

    Thank you for the update. The latest Async's MIX XL is also an excellent model.

    Checkpoint
    SDXL 1.0

    Details

    Downloads
    1,353
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/24/2024
    Updated
    4/30/2026
    Deleted
    -

    Files

    asyncsMIXXL_v30.safetensors

    Mirrors

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

    Available On (2 platforms)

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