<h1 id="preface-a3eemt7ui">Preface</h1><p>After my last computer crash I have to sort my pictures again. I found a few photos of a cat that I rescued from the street years ago. Since I wanted to see how I could use cat photos for a LoRA model anyway, I used these photos to create this model.</p><h1 id="what-the-lora-does-w33lvsgnh">What the Lora Does</h1><p>The LoRA is able to create a photo realistic red cat.</p><h1 id="trigger-words-5gx8yap8u">Trigger Words</h1><p>The trigger words for this LoRA are</p><pre><code>red cat</code></pre><h1 id="training-images-eafnht33f">Training Images</h1><p>The training image have a resolution of 1024 x 1536 pixel. The related aspect ratio is 3:2. I downscaled them, so that one side should have a length of 1024 pixel.</p><p>I used in total 19 of my best images.</p><p>Training settings was</p><ul><li><p>19 Images</p></li><li><p>38 buckets</p></li><li><p>2 repeats</p></li><li><p>Batch size 2</p></li><li><p>250 epochs</p></li><li><p>2500 learning steps</p></li></ul><h1 id="quality-of-the-created-images-9bz13ojys">Quality of The Created Images</h1><p>My first tests shows that the quality of the created images are depending on the model. Some models are better with respect to right anatomy than others.</p><h1 id="final-words-wutrbyz22">Final Words</h1><p>Have fun. Be inspired!</p><h1 id="donation-0022f23wv">Donation</h1><p> I am happy about each Buzz!</p><p>I am also happy to accept donations in one of 250+ crypto currencies:</p><p><a target="_blank" rel="ugc" href="https://nowpayments.io/donation/zentrocdot">https://nowpayments.io/donation/zentrocdot</a></p><p>Leave an comment when doing so that I know in what you are interested in.  </p>

Files with SHA256: 2ff3a69fff40ded875e8a476807c9279bf27df94ec48dd7cd3d98b11bb4a831f