CivArchive
    JAV Ai_Sayama (佐山愛) - JAV_ai_sayama_v1
    Preview 11509738Preview 11509744Preview 11509712Preview 11509711Preview 11509745Preview 11509714Preview 11509713Preview 11509715Preview 11509717Preview 11509716Preview 11509721Preview 11509735Preview 11509710Preview 11509724Preview 11509727Preview 11509747Preview 11509741Preview 11509743Preview 11509742

    Imitation model. Modelled after Japanese AV veteran Ai Sayama (佐山愛).

    the JAV Queen of thicc JAV.

    Its strange how Ai have actually debuted for almost 16 years by now. Her chests were much smaller when she debuted, but they seem larger in recent years. I suspect that she might have had minor implant surgeries to get them to look bigger. Having that said, she is still considered one of the H-cup JAV goddesses in the fanbase. Genre wise, Ai's performance is very versatile, partially attributable to her fairly long track record in the industry. Feature-wise her facial features are seemingly unique, and very recognisable, making this a very easy to execute LoRA.

    ~~~~~~~~~~~~~~~~~~~~~~~~~~
    Recommended LoRA strength: 0.8 (0.6-1.0 are plausible range dependent on checkpoints; higher values >1 dont do much, but can make thicc-ness go overboard..)

    Main Prompt:

    aisayama_jav, breasts, long hair, parted lips, teeth,

    variations: single hair bun, ponytail, tied hair,

    facial variations: parted lips, lipstick, makeup, blush, teeth, smile

    *Use of facial prompts depend on checkpoints, I didnt actually bother, since the main prompts works fine.

    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    Checkpoints that work well for this LoRA:

    1) Realisian. Best in slot. (esp for her ponytail apperances)

    2) RealisticMix. Has comparable performance with Realisian in facial resemblance. But my major issue with this is the exaggerated breast size.

    3) Other realistic checkpoints. Feel free to experiment.

    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    Note for achieving good resemblance:

    Very straightforward to use. If you are lazy, you can just use the main prompt to control for everything and apply Adetailer to fix the faces.

    Else, you can separate the prompts into 2 stages.

    1. Generate the main prompt using a LoRA strength of 0.6-0.8. I did not run into any weird body proportion issues with 0.8. so its probably safe to say that this weight is stable for use.

    2. Now depending on what you use for (1), turn on facial Adetailer, and put something like

    "face of aisayama_jav, long hair, parted lips, teeth, <lora:JAV_ai_sayama_v1_epoch_10:0.8>"

    Do remember that if you want her with her ponytail, make sure you set the prompts on both ends to reflect that. As you can see, I tend to set the LoRA weight slightly higher for Adetailer, to correct her facial features.

    set Adetailer denoise strength to 0.45-0.5. for Full body, you can try to set this higher to 0.55.

    It is still better to use AD at baseline generation (512,768 etc) and then upscale it later.

    Recommended approach: is to not use HiRes, but upscale it with img2img instead.

    Use a denoise strength of 0.20 -0.25 (anything higher will overcorrect face during the process), and turn off Adetailer. I prefer 0.2 since I use foolhardy-reMarci.

    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    Issues:

    No issues so far, apart from some badHands.

    Post-production edits/Reproducibility:

    No edits. all img2img original upscales.

    Happy prompting. And do share [SFW] creations~

    Description

    v1. Epoch #10 chosen (#12 suffer some overbleeding). Trained on 160+ photos. With more materials from recent years (i.e post breast-size enhancement Ai)

    LORA
    SD 1.5

    Details

    Downloads
    324
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/6/2025
    Deleted
    4/24/2025
    Trigger Words:
    aisayama_jav
    long hair
    brown hair
    ponytail
    breasts
    parted lips

    Files

    JAV_ai_sayama_v1-000010.safetensors

    Mirrors

    457904_training_data.zip

    Mirrors

    CivitAI (1 mirrors)