CivArchive
    illust-Anime-2D Ω IL - Omega v1
    Preview 1
    Preview 2
    Preview 3
    Preview 4
    Preview 5
    Preview 7
    Preview 8
    Preview 9
    Preview 10
    Preview 11
    Preview 12
    Preview 13
    Preview 14
    Preview 15
    Preview 16
    Preview 17
    Preview 18
    Preview 19
    Preview 20
    Preview 21
    Preview 22
    Preview 23
    Preview 24

    Supports 2D, 2.5D, anime, semi-realistic and other styles, with more consistent performance and enhanced prompt comprehension, plus boosted support for Danbooru artist styles.

    Recommended Params

    Steps: 20-40 | CFG Scale: 4-7 | Samplers: dpmpp_sde / Euler a / dpmpp2m_sde | Schedulers: beat / karras / sgm_uniform / exponential

    Upscaler: esrgan_4x / 4x-UtraSharp | AD: yolov8n_v2.pt

    VAE is integrated in this model.

    My go-to settings for it: 25 steps, 6 CFG Scale, dpmpp_sde + beat scheduler, 832x1216 resolution.

    This model was initially built to upgrade my illust-Anime-2D_IL checkpoint, but it’s undergone extensive modifications. While it shares some similarities with the original, there’s no direct iterative connection between them – so I’m releasing it as a standalone model.

    Well-crafted prompts and proper Danbooru tags are the keys to unlocking the full potential of Illustrious and NOOB. If you like this model, your feedback and post shares would be much appreciated! Hope you enjoy using it!

    Description

    Steps: 20-40, CFG scale: 4-7, Sampler: dpmpp_sde_gpu, euler,euler a,scheduler: beta,normal,simple,
    CHECKPOINT
    Illustrious

    Details

    Downloads
    17,863
    Platform
    TensorHub
    Platform Status
    Available
    Created
    1/17/2026
    Updated
    1/18/2026
    Deleted
    -

    Files

    illust-Anime-2.5D_IL_v1.safetensors

    Mirrors

    Other Platforms (TensorArt, SeaArt, etc.) (2 mirrors)