CivArchive
    Choco (Chocolate Shop) Style - Illustrious - Illustrious v2
    NSFW
    Preview 115054254
    Preview 115054288
    Preview 115397102

    The style of Choco.

    I made this lora to try and reproduce the style of Chocolate Shop.

    Illustrious v3: somewhat the same as version 2, but it is smoother and I have the feeling it is slightly better. It still needs the artist tag (choco \(chocolate shop\),) for the best result. I think the dataset is not consistent enough, but fixing that would take way to much time, and using the artist tag is faster.

    • Backgrounds that are not well tagged might create artifacts. Define a background or use simple background together with (signature, watermark, username, artist name, english text, text, dated, signature:1.5), in the negatives for best results!

    Illustrious v2: I made this lora because I noticed the old Illustrious lora trained in my early days was lacking in strength, These new lora works better, but for the best result, you best use the artist tag: choco \(chocolate shop\), It enhances your works greatly, but each on their own will give a lesser effect.

    • The dataset is trained with text and frames (but they are properly tagged). So be sure to use negative tags to counter this. If you don't know any, take a look at the demo images as a start.

    • Backgrounds that are not well tagged might create artifacts. Define a background or use simple background together with (signature, watermark, username, artist name, english text, text, dated, signature:1.5), in the negatives for best results!

    For all versions! I recommend you use: masterpiece, best quality, amazing quality, very aesthetic, high resolution, in your prompt and I myself am using the following negative prompt: text, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, lowres, (worst quality, bad quality:1.2), bad anatomy, jpeg artifacts, signature, watermark, username, signature, simple background, conjoined,

    The above showcase images were made with Addetailer extension enabled and using a face, eyes and hand model.

    This LoRa is trained on Illustrious 0.1, but I made the above showcase images in different checkpoints, because their style was more to my liking.

    The Trigger is: ch0c0,

    Advised strength: 0.6-0.9

    For more information you can take a look at the showcase images!

    Description

    FAQ

    Comments (4)

    DHYohkoJan 15, 2026· 1 reaction
    CivitAI

    Works amazing, although you really need to add the negative tags or you get a lot of text and frames.

    Ava_Choco
    Author
    Jan 15, 2026

    Yes the dataset has a bit of contamination with those things. I will add a warning about that in the description for future users.

    DHYohkoJan 17, 2026

    @Ava_Choco I got rid of it 85% of the time adding your recommended ones along with "frame, border, logo, text:1,"

    Ava_Choco
    Author
    Jan 17, 2026

    @DHYohko Yes and describing the background in detail is a thing I tend to do. Even if it is mostly "simple background" with a "colored background".

    LORA
    Illustrious

    Details

    Downloads
    431
    Platform
    CivitAI
    Platform Status
    Available
    Created
    12/24/2025
    Updated
    6/26/2026
    Deleted
    -
    Trigger Words:
    ch0c0
    choco \(chocolate shop\),

    Files

    choco_(chocolate_shop)_style_illustrious_1_5_epoch_9.safetensors