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 <a target="_blank" rel="ugc" href="https://civarchive.com/models/686704/flux-dev-to-schnell-4-step-lora">https://civarchive.com/models/686704/flux-dev-to-schnell-4-step-lora</a>(Seems to work a bit less well with <a target="_blank" rel="ugc" href="https://civarchive.com/models/678829/schnell-lora-for-flux1-d">https://civarchive.com/models/678829/schnell-lora-for-flux1-d</a>, 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-9tensor. art/models/799093298644978244/YAWC-Watercolor-5CosD6A3R20NoC-2024-11-22-23:12:45-Ep-9tensor. art/models/798371619585168991/YAWC-Watercolor-5CosD4A2R20E8-2024-11-21-00:29:10-Ep-8tensor. art/models/798765094424184653/YAWC-Watercolor-5CosD4A2R20Cap-2024-11-21-02:52:27-Ep-8Training 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-fp8Trigger: yawc1 watercolorRepeat: 20 Epoch: 8 or 9 epochs.Unet LR: 0.0005 Scheduler: cosine Optimizer: AdamW/AdamW8bitNetwork Dim: 4 Alpha 2 or Dim 6 Alpha 3

Yet Another Watercolor Style

Same dataset, but now using Florence 2 captioning.Seems a little bit less flexible compared to the "no caption" version (for example, it likes to make people sit on a chair). Also, seed to require more steps when using the Schnell 4-8 Steps LoRAs.So my recommendation is to use the "No Caption" version, but feel free to run your own tests and draw your own conclusions.Trained with 26 512x512 (downscaled from 1024x1024) images with Florence 2 caption (had to change "walking" to "running" and change "woman" to "Wonder Woman"Repeat: 20 Epoch: 8 total of 4160 stepsUnet: 0.0005 Scheduler: cosine Optimizer: AdamW Network Dim: 4 Network Alpha: 2Epoch Loss1 0.4152 0.4063 0.4034 0.3785 0.3636 0.3547 0.350 8 0.343

yawcolor_flor2_d4a2.safetensors

D4A2 Florence2

D4A2 No Cap 1.1

Files with SHA256: 444fd4fa3b6713f82cdba8df619cf5ccb620c949ee8acbc151ab282a6333e16d