CivArchive
    ๐Ÿ—ก๏ธ๐Ÿ’€ DaSiWa-Illustrious-XL ๐Ÿ’€๐Ÿ—ก๏ธ - RealAnication-IL2
    NSFW
    Preview 1
    Preview 2
    Preview 3
    Preview 4
    Preview 5
    Preview 6
    Preview 7
    Preview 8
    Preview 9
    Preview 10

    ๐Ÿ—ก๏ธ๐Ÿ’€ DaSiWa-Illustrious-XL ๐Ÿ’€๐Ÿ—ก๏ธ

    FusedWifey - Edition

    ๐Ÿ”ฎ Key Features:

    • ๐Ÿ”ฅ LoRA-Free Generations
      Generate high-quality art without stacking detailers (unless you want adding spacial styles/concepts).

    • Support of IL 2.0 features

    • Consistent characters

    • Extreme versatile (use quality prompts to get what you want)

    • Quality motions

    • ๐Ÿ”ž NSFW:

      • Enhanced ??????? + poses + framing

      • NSFW and SFW capable

      • For the love to ๐Ÿˆโ€โฌ›-Girls

    • Stable resolution support up to 1536x1536p without upscaling.

    • ๐ŸŽญ Crisp Details: Enhanced details, poses, backgrounds, outfits, and character features (all of them ๐Ÿ–ค)

    • ๐Ÿช„ Prompt Responsiveness (play with CFG (3-5).

    • ๐Ÿ“œ VAE Baked in

    • Read version details for the version you are using for more information!


    • Steps: 25-30 (I use 30 normally)

    • CFG: 3-5 (I use 3 or 4 normally)

    • Sampler: Euler

    • Scheduler: Normal or Simple

    • Resolution up to 1024x1536 (native quality).
      Standard Illustrious & SDXL resolutions also supported (1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x ??0, ??0 x 1536).

    My go to settings:

    • Aspect ratio 3:4 (basic images) or 9:16 (for i2v images)

    • 3 or 4 CFG

    • Euler/Normal

    • 30 steps


    ๐Ÿฉบ Fixes & Feedback

    • Some minor details still not perfect? Use a detailer, or inpaint with mask radius 8-60 and 0.2-0.3 strength over it.
      Most of the time you don't need unless the subject is further away.

    • If you use LoRAs, try to respect the LoRA training resolution, some LoRAs are not trained for high output and will show artefacts - than use inpaint to correct that.


    ๐Ÿ–ค Why I Made This

    I was tired of using all these embeddings, detailers, negative and quality prompting just to get a good image. Quality prompting is only used to get a specific result, not because the image will get trash without it.
    So I can just make my images with some style/character LoRAs without pushing 5-10 LoRAs into a generation.
    This checkpoint is also my personal playground.


    Closing words

    ๐ŸคฉInspired by @janxd checkpoint description! So cool!

    ๐ŸžRecommended offline Frontend/UI: SwarmUI


    I want to thank all the fantastic other creators who made super nice merges to play with!

    Description

    RealAnication IL2

    • The Illustrious 2.0 upgrade for the checkpoint

    • More Details

    • Better prompt adherence

    • Understands natural language

    • Higher resolutions from 512~1536

    • updated dataset, until 2024-08

    • More realistic style (like for i2v)

    • (Face)Detailer are recommended for full-body or landscape.

    Usage suggestions:

    Low CFG works great!

    CFG:       2.5 (3-6)
    Steps:     20-30
    Sampler:   UniPC BH2
    Scheduler: Normal

    Alternative tokens:

    โ€œadult contentโ€, โ€œr-18โ€, โ€œnsfwโ€, โ€œexplicit materialโ€, โ€œsfwโ€, โ€œsafe for workโ€