CivArchive
    Yet Another Watercolor Style - D4A2 No Caption
    NSFW
    Preview 41260127Preview 41260287Preview 41259625Preview 41259871Preview 41259662Preview 41259760Preview 41259655Preview 41260138Preview 41259758Preview 41259927Preview 41259751Preview 41259866Preview 41259903Preview 41384678Preview 41259666Preview 41537553Preview 41260286

    Yet another watercolor style, trained using synthetic images generated with SDXL and SDXL Niji SE. The goal of the LoRA is flexibility, so that it can be used with other LoRAs without introducing too much of its own aesthetics.

    Known problem with the two earlier versions: the face is always Caucasian. The problem has been fixed by mixing in images of Asians.

    All versions work well (no captioned version seems a bit more flexible though), and can produce nice images at 8 steps with https://civarchive.com/models/686704/flux-dev-to-schnell-4-step-lora

    (Seems to work a bit less well with https://civarchive.com/models/678829/schnell-lora-for-flux1-d, but the tests are not conclusive)

    The last epochs are posted here. You can find earlier epochs here:

    tensor. art/models/799475546439540972/YAWC-Watercolor-5CosD4A2R20NoC-2024-11-23-22:59:14-Ep-9

    tensor. art/models/799093298644978244/YAWC-Watercolor-5CosD6A3R20NoC-2024-11-22-23:12:45-Ep-9

    tensor. art/models/798371619585168991/YAWC-Watercolor-5CosD4A2R20E8-2024-11-21-00:29:10-Ep-8

    tensor. art/models/798765094424184653/YAWC-Watercolor-5CosD4A2R20Cap-2024-11-21-02:52:27-Ep-8

    Training parameters:

    23 to 26 512x512 (downscaled from 1024x1024) images, captioned with Florence2 or by using "no captioning" training with just the trigger "yawc1 watercolor".

    FLUX.1 - dev-fp8

    Trigger: yawc1 watercolor

    Repeat: 20 Epoch: 8 or 9 epochs.

    Unet LR: 0.0005 Scheduler: cosine Optimizer: AdamW/AdamW8bit

    Network Dim: 4 Alpha 2 or Dim 6 Alpha 3

    Description

    Training with 26 512x512 (downscaled from 1024x1024) images. No caption was used other than the trigger "yawc1 watercolor"

    Image gallery for this version is softer because they were generated at 5 steps with the Schnell LoRa. The other versions were generated at 10 steps. The seed are not kept consistent because I want to cherry-pick some better looking images.

    FLUX.1 - dev-fp8

    Trigger: yawc1 watercolor

    Repeat: 20 Epoch: 8 (total of 4160 steps)

    Unet LR: 0.0005 Scheduler: cosine Optimizer: AdamW8bit

    Network Dim: 4 Alpha 2

    Prompt: yawc1 watercolor of a blonde cowgirl in white short shorts running in a corn field

    Sampler: euler

    Epoch Loss

    1 0.421

    2 0.407

    3 0.398

    4 0.380

    5 0.361

    6 0.362

    7 0.344

    8 0.338

    LORA
    Flux.1 D

    Details

    Downloads
    178
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    11/21/2024
    Updated
    9/28/2025
    Deleted
    9/22/2025
    Trigger Words:
    yawc1 watercolor

    Files