I made this eccentric midde-aged Pokemon Gym Leader from Pastoria City, Crasher Wake. He's known for Water-Type Gym, Wrestler, and has hobby of singing of his wrestling intro song or other song that might he want to sing. I use 90+ images from various site including Google Image Search, Pinterest, Tumblr, or even TV Show.Trigger Word<pre><code>crasher_wake, crasher_wake \(pokemon\)</code></pre>Settings I Used:<ul><li>Resolution: 768x768, 960x960, 768x960</li><li>Sampling Steps: 22 - 25</li><li>Sampling Method: DPM++ 2M SDE Karras</li><li>CFG Scale: 7</li><li>Weight: 0.75 - 0.95</li></ul>Notes:If you found Crasher Wake has bloated abdomen, well it is. Crasher Wake may have decent muscular profile, but he has bloated gut.

Crasher Wake | Pokemon | SD 1.5 [Old Model]

I updated this model becuase I found out there's some plently bad images that I use in dataset. Also, I added newer, high quality, and high definition images in my dataset. Image quantity is kinda samey (only increased in single digit images), but has much higher quality ones. Here's some patch notes and updates in this model:<ul><li>Increased number of images in dataset with much more higher quality and varied images</li><li>Increased LoRA size</li><li>Increased flexibility in terms of clothings and model compatibility</li><li>Increased image resolution trained on from 512 to 640</li><li>All images trained in this model already upsized by 4x</li></ul>Notes:This model still has issue in racial bias a little bit. Crasher Wake supposed to be a Japanese middle-aged man, rather than Japanese-Cuacasian in his 40s. Idk why is this, probably the checkpoint I used is bit in bias or I didn't add "japanese, middle-aged, 40 years old" like that. Btw, you can try that.

Files with SHA256: 03e20ee22d3c2134e96c4ff9a041fb6d5788ab1a015ffb1ba83b7dc13a285a1e