<p><strong>Please share your creations. I would love to see how you have used the LoRA.</strong></p><p>The Whimsical London LoRA was trained to produce images that have an English feel, though other images can be created. It has a touch of whimsy and a little abstract style thrown in.</p><h2 id="v03">V03</h2><p>When it came time to produce versions for Qwen and SD3.5, I discovered that the training images produced too many artifacts for clean results. I produced new training images and regenerated each of the models I support. The results are inevitably different than the preceding version, but may still be of interest.</p><h2 id="v02"><strong>V02</strong></h2><p>This version has more of the atmosphere, whimsy and character I was hoping to produce in version 1. Start with a weight of 0.85.</p><p></p><h2 id="v01"><strong>V01</strong></h2><p>Weight range: 0.6 - 1.2, depending on the intensity of effect desired. Start around 0.8 and go from there. This version is more realistic than V02</p><p></p>

Whimsical London - CE

WhimsyLondon2_CE_SDXL.safetensors

V02 - SDXL

V03a - Qwen

Files with SHA256: 75fdd07640fa6992e45782b2f80e763dfb2d37757206b39efa9e9c2568038f9f