[SD 1.5][LORA]Bob's Burgers - LoRA v1.0
<h1>Bob's Burgers LoRA Overview</h1><p>This LoRA was trained on the animated sitcom created by Loren Bouchard.It includes concepts for all 5 members of the Belcher family (Bob, Linda, Louise, Tina, and Gene) as well as Teddy, for a total of 6 concepts.</p><p></p><h2>LoRA - What is it?</h2><p>Well, it is an acronym for <strong>Low-rank Adaptation</strong>, but that doesn't really say what it is. LoRA is a method used for quick fine-tuning of diffusion models. What you end up with after training is a much smaller 'model' that works with your other models. It is used somewhat like a hypernetwork, but currently the tool most people use with LoRA models is Automatic1111.</p><p></p><h2>Recommended Settings</h2><ul><li><p>LoRA strength - between 0.7 and 1.0 give the best results. I use 0.8 mostly, but you can play around with the strength and tweak to your liking</p></li><li><p>I used SD 1.5 to train it and get good results with most models based on that, but it also works really well with <a rel="ugc" href="https://civitai.com/models/1366/elldreths-lucid-mix">Elldreth's Lucid Mix</a> and <a target="_blank" rel="ugc" href="https://civitai.com/models/3848/theallys-mix-ii-churned">TheAlly's Mix II: Churned</a>. You might also find it works well with other models, so feel free to share!</p></li><li><p>Highres.fix is great with this LoRA but you can get good images without it</p></li></ul>
页:
[1]