CivArchive
    Amy Rose - v1.0
    NSFW
    Preview 104547722
    Preview 104522231
    Preview 104522244
    Preview 104522242
    Preview 104522233
    Preview 104522241
    Preview 104522240
    Preview 104522236
    Preview 104522232
    Preview 104522249
    Preview 104522239
    Preview 104522248
    Preview 104522237
    Preview 104522247
    Preview 104522251
    Preview 104522234
    Preview 104522243
    Preview 104523230
    Preview 104522230
    Preview 104545723

    🦔 Amy Rose LoRA (SDXL)

    What does your model do?

    Faithfully recreates Amy Rose from Sonic the Hedgehog in SDXL quality, capturing her iconic design and cheerful personality for high-quality character generation.

    What's it for?

    - Fan art & illustrations

    - Character reference sheets

    - Personal creative projects

    - SFW Sonic fan content

    What is your model good at?

    ✅ Accurate Amy Rose appearance (pink fur, red dress, Piko Piko hammer)

    ✅ Expressive poses & consistent character

    ✅ Works with anime & semi-realistic styles

    ✅ Detailed accessories and multiple outfits

    What should it be used for?

    - Fan creations

    - Artistic experiments

    - Personal entertainment

    - Safe content only

    What is your resource bad at?

    ❌ NSFW content

    ❌ Extreme body modifications

    ❌ Cross-universe fusions

    ❌ Photorealistic rendering

    ❌ Background generation

    How should it not be used?

    - Adult/explicit content

    - Commercial merchandise without SEGA permission

    - Negative misrepresentation

    - Illegal/harmful applications

    🎯 Recommended Usage

    Trigger: Amy Rose (exact capitalization)

    Best prompts:

    ```

    Amy Rose, pink hedgehog, red dress, Piko Piko hammer, cheerful expression, anime style, vibrant colors, dynamic pose

    Amy Rose with hammer, determined expression, Sonic game style, green hill zone background

    Amy Rose smiling, classic Sonic aesthetic, detailed fur, red boots, holding hammer

    ```

    Training Details:

    - Base Model: NoobAI-XL v1.1

    - Resolution: 1024x1024

    - Network Dim: 8, Alpha: 4

    - Optimizer: AdamW8bit

    - LR: UNet 3e-4, Text Encoder 6e-5

    Base compatibility: SDXL models, especially anime-focused

    Good morning, dear creators! We'd love to hear your comments ❤️I sincerely hope you like it. It took us a long time to put together the dataset.

    Description

    Training Details - Version 1.0:

    • Base Model: NoobAI-XL v1.1

    • Dataset: 149 images × 2 repeats = 298 steps

    • Training: 1 epochs, 75 total steps

    • Resolution: 1024x1024

    • Network: LoRA (Dim 8, Alpha 4)

    • Batch Size: 4

    • Learning Rate: UNet 3e-4, Text Encoder 6e-5

    • Optimizer: AdamW8bit

    • Scheduler: Cosine with Restarts (3 cycles)

    Base compatibility: SDXL models, especially anime-focused

    LORA
    NoobAI

    Looks like we don't have an active mirror for this file right now.

    CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.

    Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.

    Details

    Downloads
    14
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    10/6/2025
    Updated
    7/27/2026
    Deleted
    10/7/2025

    Files

    Amy-01.safetensors

    Mirrors

    CivitAI (1 mirrors)