CivArchive
    Preview 13639335
    Preview 13639332
    Preview 13639327
    Preview 13639334
    Preview 13639328
    Preview 13639341
    Preview 13639337
    Preview 13639342
    Preview 13639345
    Preview 13639344
    Preview 13639346
    Preview 13639349
    Preview 13639350
    Preview 13639351
    Preview 13639348
    Preview 13639354
    Preview 13639353
    Preview 13639352
    Preview 13639364
    Preview 13639369

    Model Details.

    Recommended settings

    it’s recommended to use a lower classifier-free guidance (CFG Scale) of around 2 - 3, sampling steps between 6 and 8, and to use Euler Ancestral(Euler A) as a sampler.

    thanks to TURBO technology it takes only a few steps.

    Suggested prompts : "masterpiece, best quality, very aesthetic, absurdres,newest,ai-generated," add "intricate" to enhance fine details. remove "ai-generated" to have more anime style picture.

    Suggested negative prompts : "nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, abstract,"

    Notes

    Based on VXP XL(Hyper), Animagine XL v3.1 and BreakDomain XL. NW-VXP XL falls under Fair AI Public License 1.0-SD license, which is compatible with Stable Diffusion models’ license. Key points:

    1. Modification Sharing: If you modify NeverWinter Mix, you must share both your changes and the original license.

    2. Source Code Accessibility: If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.

    3. Distribution Terms: Any distribution must be under this license or another with similar rules.

    4. Compliance: Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values.

    Description

    Played with the block weights. Might give some flat results as it's still under testing. Recommended to use 3 for CFG and 7 or 8 for sampling steps. Sampler should be Euler A and hires steps at 10 or 20, or depends on your taste. Had some great results with 600x900 and 600x600 reso, upscaler is r-esrgan 4x+anime 6B

    Checkpoint
    SDXL 1.0

    Details

    Downloads
    749
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/26/2024
    Updated
    1/10/2026
    Deleted
    -

    Files

    nwVXPXL_v15Test.safetensors

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)

    Available On (1 platform)