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

Tweaked the dataset slightly with a new set of 5 Asian images (reduce from 8 so that the "Asianess" is less proununced. the new ratio is 5/26 compared to 8/23 before)This is Epoch 9, earlier epoch can be found here: tensor. art/models/799475546439540972/YAWC-Watercolor-5CosD4A2R20NoC-2024-11-23-22:59:14-Ep-9FLUX.1 - dev-fp8Trigger: yawc1 watercolorRepeat: 20 Epoch: 9 total: 4500 steps (25 images)Unet LR: 0.0005 Scheduler: cosine Optimizer: AdamWNetwork Dim: 4 Alpha: 2Epoch Loss1 0.4172 0.4083 0.4034 0.3995 0.3736 0.3627 0.3638 0.3549 0.350

YAWC5.Watercolor.5CosD4A2R20NoC.Training.Set.zip

yawcolor_nocap1_d4a2.safetensors

D4A2 No Cap 1.1

D6A6 No Caption

D4A2 Florence2

D4A2 No Caption

YAWC Watercolor 5CosD4A2R20NoC 2024-11-23 22:59:14

c07471bb-69b9-40bd-bb32-505ec550f3fe.TA_trained.safetensors

Ep 9

Files with SHA256: 46685cc3ce75426301dffefedb4264ac7b07929402255cb790ccd98989f6fc69