CivArchive
    Axiom - v1.0 (fp8)
    NSFW
    Preview 122567263

    *some previews may be unavailable here due to auto-censorship. To see the full range of model capabilities (including NSFW), view the complete gallery on Telegram

    Axiom is a complex merge designed to solve the common trade-offs in Illustrious/Noob-AI models. While base models are diverse but unstable, and specialized models offer stability at the cost of a "hard-coded" style, Axiom bridges this gap. It eliminates the anime-only bias of Illustrious and the loss of character authenticity found in realistic models.

    Key Features:

    • Perfect Balance: A versatile foundation that maintains stability without sacrificing diversity. It covers anime, illustrations, 3D, and semi-realism within a single, pretty balanced model.

    • Advanced-User Ready: Optimized for broad prompt interpretation - delivering authentic ethnic features and complex textures that standard anime models often simplify.

    • Superior Control: Extremely high compatibility with ControlNet and IP-Adapter, allowing for precise scene, pose, and style management.

    • Universal LoRA Support: High compatibility with both Illustrious and Noob-AI LoRAs.


    Technical Guide

    Recommended Settings:

    • Generation: Euler a Polyexponential | 30 Steps | CFG 5.5~ | Default Illistrious/Noob-AI Resolutions

    • Upscaling: Hires/SD Upscale x1.5–2.0 | Denoising ≤ 0.46 | Steps ≤ 23

    • Upscalers: ESRGAN, UniScale Balanced, or NKMD SIax (sharp upscalers recommended)

    • Software: WebUI - ReForge ("Old" branch recommended for bug-free ControlNet support)

    Prompting Structure:

    • Positive: [subject/scene], masterpiece, very awa, best quality, absurdres, newest

    • Negative: lowres, (worst quality, bad quality:1.2), text, watermark, old, [negative]

    ControlNet & IP-Adapter:

    • IP-A: Weight 0.66–0.9 | Start 0.11–0.33 | End 0.66–1.0

    • General Tips: Avoid 1.0 weight on all parameters. Lineart Realistic is strongly recommended for high-fidelity textures.


    • Notes:

      • Some previews include post-processing (ADetailer/External edits) to demonstrate maximum potential for advanced workflows.

      • Metadata is intentionally stripped from previews to prevent simple copy-pasting. As this model is built for advanced users, the goal is to encourage unique creations rather than replication.

      • For support, discussions, or any questions, feel free to join the Telegram channel.


    License & Usage Terms

    By downloading or using Axiom, you agree to the following:

    • Personal/Commercial Renders: Allowed for individuals (selling images is okay).

    • Corporate/Entity Use: Strictly prohibited without explicit permission. Includes any platform or service where the model is hosted, regardless of their own Terms of Service.

    • No Hosting: Uploading or hosting on any generation services/cloud platforms is strictly prohibited.

    • No Derivatives: Using Axiom as a base for merging, training, or selling new models/selling the model itself is prohibited.

    Description

    Optimized Hybrid (FP8 UNet / FP16 CLIP)


    Key Benefits (compared to FP16):

    • VRAM Optimization: Lower memory footprint (depends on hardware and software configuration).

    • Storage Optimization: ~37% smaller file size (4.07GB vs 6.46GB).

    • Performance: Native hardware acceleration for RTX 40xx/50xx.

    • Visual Fidelity: High accuracy with subtle variations in fine details.

    FAQ

    Checkpoint
    Illustrious

    Details

    Downloads
    22
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    2/27/2026
    Updated
    4/27/2026
    Deleted
    3/25/2026

    Files

    axiom_v10Fp8.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)