<h2 id="attention:-it-is-strongly-recommended-to-enable-adetiler-to-repair-facial-details.">Attention: It is strongly recommended to enable ADetiler to repair facial details.</h2><h2 id="about-this-version">About this version</h2>As you can see, this model has been updated. The inspiration came from an image with a porcelain-doll texture that caught my eye, so I tried to recreate the exact look I wanted through a mix of model merging, LoRA blending, and a few tiny tweaks. Strictly speaking, the result leans toward a realistic style—but that doesn’t matter; what matters is whether you all like it.By the way, I think this bug (or rather, this workaround for a logic error) is actually a source of inspiration—even if the fix itself is a bit crude. The rest of this post will mainly explain the bug and the blunt-yet-effective way to get around it. ## I. Bug Cause The core issues in SuperMerger's <code>network_lora.py</code> code are: 1. Confused type judgment logic: The original code incorrectly classified <code>MultiheadAttention</code> (core type of SDXL's TE2 layer) into the <code>is_linear</code> (linear layer) check. However, <code>MultiheadAttention</code> is a composite module containing multiple sub-linear layers, and processing it as an ordinary linear layer easily triggers type incompatibility. 2. Lack of targeted adaptation: The code had no separate handling for <code>MultiheadAttention</code> layers. When encountering TE2 layers in SDXL LoRA, it directly threw an "unsupported layer type" error, making it impossible to merge LoRAs containing TE2 layers. ## II. Solution 1. Split type judgment: Added explicit <code>is_multihead_attn</code> check, removed <code>MultiheadAttention</code> from <code>is_linear</code>, and prioritized processing this type of composite layer to avoid logical conflicts. 2. Adapt to composite layer structure: When detecting <code>MultiheadAttention</code> layers, adjusted LoRA weight shape through <code>weight.reshape</code> and created compatible linear layers to accept weights, ensuring TE2 layers can be loaded normally. 3. Enhance error verification: Added weight shape validity checks, threw detailed errors (including target/actual shapes) if <code>reshape</code> failed, and unified error handling logic for easier problem localization. The optimized code supports SDXL's TE2 layer LoRAs without damaging original linear/convolutional layer functions, reducing the risk of hidden bugs.Here are the suggested prompt snippets you can add—tweak weights or phrases as you like.Positive (add to the main prompt)masterpiece,ultra-HD,best quality,high resolution,ultra detailed,intricate,sharp focus,8k,high definition,detailed texture,aesthetic,Regular layout,SmoothNoob_Quality,Negative (add to the negative prompt)worst quality, low quality, displeasing, text, watermark, bad anatomy,blurry,text, artist name, signature, deformed hands, missing finger,

Files with SHA256: d1691a474b1162cf473af5505cca6f43d0b23191296103fe22e2a38c63044aa2