CivArchive
    Nectarine Nymphs - Model 14 - Illustrious - V3.5
    NSFW
    Preview 129736522
    Preview 129736519
    Preview 129736523
    Preview 129736526
    Preview 129736529
    Preview 129736527
    Preview 129736530
    Preview 129736533
    Preview 129736534
    Preview 129736535
    Preview 129736537
    Preview 129736538
    Preview 129736540
    Preview 129736541
    Preview 129736542

    Uploaded by request. A merge of a few custom checkpoints I made in my personal collection. A specialty with the female form in a hotly saturated cartoon style. SFW/NSFW

    Anima V1

    V1 is a little bit rigid with some prompts. Upping weights on tags slightly circumvents any issues I've had.

    Trained at 768x768 - 2D Illustration

    Sampler/Scheduler: ER SDE / Beta

    Steps: 28-32

    CFG best at 4

    VAE: https://civarchive.com/models/1864281/qwen-image?modelVersionId=2110009

    Anima V1 Turbo AIO (Optional Files)

    Sampler/Scheduler: ER SDE / Beta

    Steps: 8-16

    CFG best at 1.5

    Illustrious V4.5

    Trained at 1024x1024 - Extra Strong semi-realistic tones

    Sampler/Scheduler: DPM ++2M/Karras

    Steps: 25-30

    CFG best at 4

    VAE: https://civarchive.com/models/140686/fix-fp16-errors-sdxl-lower-memory-use-sdxl-vae-fp16-fix-by-madebyollin

    Adetailer is recommend for face sizes lower than 1/8th of the generated image size.

    Optionally emphasize the realism by using the prompt:
    masterpiece, ultra-detailed, cinematic, highres, soft shadows, global illumination, volumetric lighting, subsurface scattering, bounce lighting, physically accurate lighting,

    Illustrious V4

    Trained at 1024x1024 - Even stronger western and semi-realistic 2.5D tones

    Sampler/Scheduler: DPM ++2M/Karras

    Steps: 20-25

    CFG best at 5

    VAE: https://civarchive.com/models/140686/fix-fp16-errors-sdxl-lower-memory-use-sdxl-vae-fp16-fix-by-madebyollin

    Adetailer is recommend for face sizes lower than 1/8th of the generated image size.

    Optionally emphasize the realism by using the prompt:
    masterpiece, ultra-detailed, cinematic, highres, soft shadows, global illumination, volumetric lighting, subsurface scattering, bounce lighting, physically accurate lighting,

    Illustrious V3.5

    Trained at 1024x1024 - Strong Flat Vectors

    Sampler/Scheduler: DPM ++2M/Karras

    Steps: 20-25

    CFG best at 4

    VAE: https://civarchive.com/models/140686/fix-fp16-errors-sdxl-lower-memory-use-sdxl-vae-fp16-fix-by-madebyollin

    Adetailer is recommend for face sizes lower than 1/8th of the generated image size.

    Optionally emphasize the realism by using the prompt:
    masterpiece, rich colors, colored_lineart, no background, solid background, vectors, solid colors, accurate lineart, thick line art,

    Illustrious V3

    Trained at 1024x1024 - Vector Adjacent 2D

    Sampler/Scheduler: DPM ++2M/Karras

    Steps: 20-25

    CFG best at 5

    VAE: https://civarchive.com/models/140686/fix-fp16-errors-sdxl-lower-memory-use-sdxl-vae-fp16-fix-by-madebyollin

    Adetailer is recommend for face sizes lower than 1/8th of the generated image size.

    Illustrious V2

    Trained at 1024x1024 - Stronger western and semi-realistic 2.5D tones

    Sampler/Scheduler: DPM ++2M/Karras

    Steps: 20-30

    CFG best at 3.5 - 5

    VAE: https://civarchive.com/models/140686/fix-fp16-errors-sdxl-lower-memory-use-sdxl-vae-fp16-fix-by-madebyollin

    Adetailer is recommend for face sizes lower than 1/8th of the generated image size.

    Emphasize the realism by using the prompt:
    masterpiece, ultra-detailed, cinematic, highres, soft shadows, global illumination, volumetric lighting, subsurface scattering, bounce lighting, physically accurate lighting,

    Illustrious V1

    Trained at 1024x1024

    CFG best at 3.5 - 5

    CD-Tuner - Contrast(con1) +6 for darker images in model example images

    --

    Pony V1

    Trained with SD15 dataset. Leaning towards solid vector coloring.

    Pony V2

    More semi-realistic tones and lighting. Added details and removed common errors.

    Pony V3

    Sketchy throwback style. "Cuter" and more expressive.

    Pony V4

    Strong semi-realistic tones.

    CD-Tuner - Contrast(con1) +6 for darker images in model example images

    --

    SD 1.5

    Works best at 768x768 but I've had pleasing results at 512x1024 and 1024x1024.

    I've found that an abundance of negative prompts hurt the style, but by all means can be used.

    Character LoRAs have little issue also.

    ADetailer recommended for portraits sized 512x768, 512x1024 and 768x1024.

    Extensively tested with LCM FP8 precision.

    Description

    FAQ

    Comments (4)

    JaggedBeauty743May 10, 2026· 1 reaction
    CivitAI

    Big fan. Keep up the effort, and GG!

    UncleJert
    Author
    May 11, 2026

    Glad you enjoy it! Thank you for the kind words.

    bdole2044May 19, 2026
    CivitAI

    Who is Katriona Lean Mac Giolla Ruaidh?

    UncleJert
    Author
    May 20, 2026

    Waaaay back in the day a million years ago in 2024, there was a trick to achieve unique faces in stable diffusion by typing long names. I THINK it still works. But that prompt for that character is still hanging on to that name still. This is the site I used to generate it - https://www.behindthename.com/random/

    This technique still works, but make sure you use middle names. Like 'Steve Michael Flynn' and ect.

    Checkpoint
    Illustrious
    by UncleJert
    Download (Beta) View on CivitAI
    sexy
    style
    solo focus
    girls
    women
    toon
    pinup girl

    Details

    Downloads
    244
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/5/2026
    Updated
    8/12/2026
    Deleted
    -
    Trigger Words:
    masterpiece, rich colors, colored_lineart, no background, solid background, vectors, solid colors, accurate lineart, thick line art,

    Files

    nectarineNymphsModel_illustriousV35.safetensors

    Size:
    6.46 GB
    SHA256:
    93254df653adc2663151811af538e7561d56942e6b4765d0124c9833a327d3c3

    Mirrors

    CivitAI (1 mirrors)

    fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors

    Size:
    319.14 MB
    SHA256:
    235745af8d86bf4a4c1b5b4f529868b37019a10f7c0b2e79ad0abca3a22bc6e1

    Mirrors

    HuggingFace (262 mirrors)
    CivitAI (5 mirrors)
    CivitasBay (1 mirrors)
    ModelScope CN (1 mirrors)
    ShakkerAI (1 mirrors)