CivArchive
    Chelsea Wang for Flux - v1.0
    Preview undefined
    Preview undefined

    Chelsea is 32AAA cup. Yes, triple-A is an actual thing. Most women with that bra size simply wear sports bras. This size is so uncommon that very few brands produce this. The most famous is Little Women, which sells bras for $100+ per tiny bra. AAA is truly flat-chested. Absolutely nothing there. Try some nude generations to see how good her body looks.

    Generations are fantastic. Enjoy

    Training details:

    • Steps: 3,000, 2 batch (ai-toolkit)

    • Samples: 50 samples per image

    • Trigger word: ch3l534W4ngAsian (not needed)

    • Linear/Alpha 32

    • Learning rate: 0.0001 (bf16)

    • Image size: 1024x1024

    • Dataset: 29 detailed photos of her face, head, and body - now has good nudes

    • Training prompts: Tried to prompt out makeup and jewelry

    ComfyUI usage:

    Please note that all of my sample images double as a ComfyUI workflow! Simply drag any of the sample images into ComfyUI and it will open the entire workflow, set the seed, and use my same configuration. I typically use LLM generation but chose not to do so for these tests; instead, I used a more basic workflow.

    Comfy settings:

    • Steps: 35

    • Guidance: 3.5

    • Sampler: DPM++ 2M, Beta

    Description

    LORA
    Flux.1 D

    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
    26
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    2/22/2025
    Updated
    5/10/2026
    Deleted
    5/23/2025

    Files

    Chelsea_Wang.safetensors

    Mirrors

    CivitAI (1 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.