CivArchive
    Preview 1726293
    Preview 1726294
    Preview 1726296
    Preview 1726297
    Preview 1726300
    Preview 1726299
    Preview 1726298
    Preview 1726301
    Preview 1726303
    Preview 1726302
    Preview 1726310
    Preview 1726308
    Preview 1726309
    Preview 1726306
    Preview 1726307
    Preview 1726311

    About the model:

    My goal with this mix was to create a mostly 2d anime style model that responds well to varied prompts, including a relatively wide range of existing characters without the need of additional LoRAs. NSFW was not a focus for this model, but it can still do it. I have done little testing on LoRA compatibility with this model because I primarily use style LoRAs and this model already has the style that I wanted it to have.

    I'd love to see what you create with this model!

    Prompting:

    Kakigori responds best to booru style prompting, although it can handle some natural language prompting.

    Example prompt:

    kirisame marisa, blonde hair, side braid, waist apron, witch hat, hat bow, yellow eyes, superb, looking down, splashing in a stream, nature, outdoors

    I find that a simple negative prompt without any negative embeddings has worked best for me.
    Example negative prompt:

    (Worst Quality, Low Quality:1.2), border, nsfw, skimpy, grayscale, multiple_girls, (watermark:1.2)

    Recommended settings:

    Clip skip: 2
    
    Base Resolution: ~512x768 or 768x512
    
    Hires. fix: 4x_fatal_Anime_500000K_G / Upscale by: 1.5+ / Denoising strength: 0.48
    
    Adetailer: face_yolov8n
    
    Sampler: DPM++ 2M Karras/DPM++ 2M SDE Karras
    
    CFG: 7.5 / Steps : 20

    Credits:

    I would like to give thanks to the authors of the following models which were included in this merge. If you like my merge then I would encourage you to try these out as well.

    AuroraONE by Luna

    Toonyou - JP - Alpha 1 by Bradcatt

    ExpMix_Line - V3 by Mods13

    (VAE) kl-f8-anime2 by hakurei

    Why baked VAE?:

    Because I see too many people using models without the correct VAE too often, the impact to file size is tiny, and I don't expect this model to be great for training from anyways. You can still load whichever VAE you would like in WebUI and you're more than welcome to prune the VAE yourself if you'd prefer that. The VAE I used is a customized version of kl-f8-anime2 with lower contrast than the official version. If you would like a copy of the VAE baked into this model you can get WD1-4-kl-f8-anime2-bless09 here.

    This model may not be used on any paid generation services. You may not sell this model or any merges that contain it. This model is for personal/private use. Commercial use is not authorized.

    You are more than welcome to include this model in merges as long as those merges adhere to the same license as this model. If you upload your merge all I ask is that you include a link to this model in the about section like I have done here.

    Description

    v2 should give good hands far more often. I tried to keep the style as close to the original as possible while improving the quality of generations. This version includes the same modified version of the Waifu-Diffusion anime2 vae baked in. You may find that the lower contrast NAI based VAEs are too washed out for this model.

    It uses Kakigori_v1 as the base with the following resources merged into it.
    [Awooooooo/Awoo7 by yoinked](https://huggingface.co/yoinked/merges)

    [vanilla by NoCrypt](https://huggingface.co/NoCrypt)

    [Lilliput by Cinsdia](https://civitai.com/models/76800)

    [ssambateaLoconStyleV2 by AshtakaOOf](https://huggingface.co/AshtakaOOf/ssambatea-locon)

    FAQ

    Comments (8)

    BradcattJul 26, 2023
    CivitAI

    So cute! Thanks to people like you, there's no reason to update TY - JP ๐Ÿ˜‚

    nubby
    Author
    Jul 26, 2023

    No! Please don't say that! I'd love to see an updated TY-JP ๐Ÿฅน

    Thank you for all of the work you put into your models!

    MarkWarJul 26, 2023
    CivitAI

    Great model!!! tested with my usual prompt and stunning result, i hope to see a lot of things from this creator!

    nubby
    Author
    Sep 3, 2023

    I've been a bit distracted by BG3 lately, but I hope to make some more improvements to this model and maybe start something new before too long.

    imakesoundSep 15, 2023
    CivitAI

    Thank you so much, this is one of my favorite models, thank you for doing something different, hoping for an xl version or a v3!

    nubby
    Author
    Sep 16, 2023

    An XL version is unlikely from me any time soon since I don't really use SDXL. I do have a few ideas I'd like to try for V3 or possibly an alternate version of this model when time allows though. I'm glad you're enjoying the model! I've had a lot of fun making and using it myself and it's nice to know that other people are benefiting from it too.

    nubby
    Author
    Oct 20, 2023

    Just released V3. I hope you enjoy!

    1074279Sep 18, 2023ยท 2 reactions
    CivitAI

    Hands-down one of the best models I've seen in SD1.5 and my favorite by a large margin. Everything it produces is adorable, and it is highly flexible in what it can produce.

    Despite the comment in the description, it handles LoRA very well and I've taken to running all of mine through this checkpoint as part of the testing steps if only because the output is gorgeous.

    Thank you for putting together such a masterpiece.

    Checkpoint
    SD 1.5

    Details

    Downloads
    5,079
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/26/2023
    Updated
    5/13/2026
    Deleted
    -

    Available On (1 platform)

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