This model helps you create Sackboy characters. It's a great improvement from the SD1.5 model but could still use a second pass.<h2 id="usage-km3el46iv">Usage</h2>Use the trigger word: "sackboy" or "sackgirl" or "sackbaby" along with the LoRA to activate it.Example prompt: &lt;lora:SackpeopleCharacterStyleSDXL:1&gt; sackboy Bruce Wayne (Batman)Note:I may be using the following extensions in the reference images: FreeU or ADetailer / Face Editor. I may also be using a specific Hires Checkpoint (swaps to another model when doing the hires steps). If your results don't match mine exactly, this may explain why.<h2 id="tips-and-tricks-g5z8bxoiv">Tips and tricks</h2>You may want to use words like <code>open mouth</code> to get rid of the weird mouth artifacts. The model should use a second training pass with a generated dataset.<h2 id="suggested-negative-prompt-nwx0yg0cn">Suggested Negative Prompt</h2><pre><code>watermark, text, lips, lip, double_chin, chin, tongue</code></pre><a target="_blank" rel="ugc" href="https://civarchive.com/articles/2138/lora-training-data-upload-to-civitai">Link to Training Data</a>Like it?<a target="_blank" rel="ugc" href="https://ko-fi.com/mnemic">https://ko-fi.com/mnemic</a><a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/mnemic">https://www.buymeacoffee.com/mnemic</a>

Sackboy Character Style -  SDXL

Sackboy Character Style Dataset v1.zip

SackpeopleCharacterStyleSDXL.safetensors

v1.0

This model helps you create Sackboy characters. It's a great improvement from the SD1.5 model but could still use a second pass.<h2 id="usage-km3el46iv">Usage</h2>Use the trigger word: "sackboy" or "sackgirl" or "sackbaby" along with the LoRA to activate it.Example prompt: &lt;lora:SackpeopleCharacterStyleSDXL:1&gt; sackboy Bruce Wayne (Batman)Note:I may be using the following extensions in the reference images: FreeU or ADetailer / Face Editor. I may also be using a specific Hires Checkpoint (swaps to another model when doing the hires steps). If your results don't match mine exactly, this may explain why.<h2 id="tips-and-tricks-g5z8bxoiv">Tips and tricks</h2>You may want to use words like <code>open mouth</code> to get rid of the weird mouth artifacts. The model should use a second training pass with a generated dataset.<h2 id="suggested-negative-prompt-nwx0yg0cn">Suggested Negative Prompt</h2><pre><code>watermark, text, lips, lip, double_chin, chin, tongue</code></pre><a target="_blank" rel="ugc" href="https://civitai.com/articles/2138/lora-training-data-upload-to-civitai">Link to Training Data</a>Like it?<a target="_blank" rel="ugc" href="https://ko-fi.com/mnemic">https://ko-fi.com/mnemic</a><a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/mnemic">https://www.buymeacoffee.com/mnemic</a>

Files with SHA256: e664af52044d17c248e0038a946541dc15ba54e26ad7eec913e248715e459c6a