CivArchive
    Shyvana (2026 VGU Rework) | League of Legends | In-Game Model LoRA - v1.2 - Illustrious
    NSFW
    Preview 126177580
    Preview 126177579
    Preview 126177578
    Preview 126177581
    Preview 126177575
    Preview 126177576
    Preview 126177577

    Trained on official in-game model + high-quality shots from the "Forged in Fury" cinematic for accurate colors, lighting, and details.

    How to Use It Effectively

    Trigger Word: driftpixel_shyvana

    ⚠️ Important: Do not use the trigger word by itself — results will be half-baked. Always combine it with detailed descriptions of pose, expression, outfit, lighting, and mood for the best quality.

    PICK THE RIGHT VERSION!

    v1.0+ – Illustrious
    v2.0 – Pony
    • LoRA Weight: 0.9 – 1.2

    • Sampler: Euler a (recommended) Alternative: DPM++ 2M Karras

    • Scheduler: Normal or Beta 1.1

    • Steps: 20 – 40

    • CFG Scale: 5 – 7

    • Resolution: 768×1024 (great starting point) I often use 832×1216

    Recommended Universal Negative Prompt:

    low quality, worst quality, blurry, jpeg artifacts, bad anatomy, bad hands, deformed, distorted, disfigured, extra limbs, missing limbs, malformed limbs, fused fingers, too many fingers, mutated hands, poorly drawn hands, poorly drawn face, long neck, gross proportions, cropped, out of frame, watermark, text, signature, logo, username

    Bonus for ComfyUI Users

    A full ComfyUI workflow is embedded in the metadata of every sample image I uploaded. Just download any showcase image and drag & drop it into ComfyUI — it will load the complete workflow automatically.

    This LoRA represents many hours of careful training and testing. If you find it useful, please 👍 like, 💬 leave a comment with your results, and feel free to ⚡ tip. it really helps support future projects!

    Description

    Base model: WAI-illustrious-SDXL

    Drastically improve the feeling of the character and made it easier to work it. Now her dragon tail and heel blade should be way way more consistent... and it should feel more like the in-game counterpart. (as intended)

    Known issues that i give up fixing...

    • The image may come out a little too saturated (i don't know why, try a different sampler and scheduler)

    • Really weak when generating "full body" shots, i recommend using "cowboy shot"

    • Super up-close image may be slightly hard to generate

    • The armor shoulder tend to always generate on the left of the image no matter what and it might be hard to change it's position. (This is my fault because i didn't alternate her armor when trained the LoRa)

    FAQ

    LORA
    Illustrious

    Details

    Downloads
    50
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/2/2026
    Updated
    4/27/2026
    Deleted
    -
    Trigger Words:
    driftpixel_shyvana, 1girl, solo, dragon girl, purple skin, long blonde hair, yellow eyes, orange sclera, reptilian pupils, slit pupils, pointy ears, horns, dragon horns, tail, dragon tail,
    armor, silver breastplate, brown leather pants, spike on shoulders,
    claws
    muscular female
    sharp teeth, fangs

    Files

    Shyvana_DriftPixel_v1.2.safetensors

    Mirrors