{"id":1386,"date":"2023-06-21T09:33:07","date_gmt":"2023-06-21T03:33:07","guid":{"rendered":"https:\/\/magiteker.com\/?p=1386"},"modified":"2023-06-22T00:20:15","modified_gmt":"2023-06-21T18:20:15","slug":"resource-dreambooth-training-readme","status":"publish","type":"post","link":"https:\/\/magiteker.com\/index.php\/2023\/06\/21\/resource-dreambooth-training-readme\/","title":{"rendered":"Resource: Dreambooth Training README"},"content":{"rendered":"\n<p>&#8211; <a href=\"https:\/\/github.com\/bmaltais\/kohya_ss\/blob\/master\/train_db_README.md\" target=\"_blank\" rel=\"noreferrer noopener\">Github<\/a><\/p>\n\n\n\n<p>README describing proper methods for constructing a dataset.<br><br>According to the README Regularization images allow for prior preservation of a models existing dataset.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Regularization images should be generated before training from the base model.<\/li>\n\n\n\n<li>Image classification should be a generic term ( i.e. person, cat, dog, man, woman ).<\/li>\n\n\n\n<li>Most experiments suggest 200 to 300 regularization images per class improve training accuracy.<\/li>\n\n\n\n<li>In order to include classification in a data set directory naming convention is as follows: &lt;number of repeats&gt;_&lt;data keyword&gt; &lt;class keyword&gt;.<br><\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"370\" data-attachment-id=\"1404\" data-permalink=\"https:\/\/magiteker.com\/index.php\/2023\/06\/21\/resource-dreambooth-training-readme\/image-1\/\" data-orig-file=\"https:\/\/i0.wp.com\/magiteker.com\/wp-content\/uploads\/2023\/06\/image-1.png?fit=800%2C370&amp;ssl=1\" data-orig-size=\"800,370\" data-comments-opened=\"0\" data-image-meta=\"{&quot;aperture&quot;:&quot;0&quot;,&quot;credit&quot;:&quot;&quot;,&quot;camera&quot;:&quot;&quot;,&quot;caption&quot;:&quot;&quot;,&quot;created_timestamp&quot;:&quot;0&quot;,&quot;copyright&quot;:&quot;&quot;,&quot;focal_length&quot;:&quot;0&quot;,&quot;iso&quot;:&quot;0&quot;,&quot;shutter_speed&quot;:&quot;0&quot;,&quot;title&quot;:&quot;&quot;,&quot;orientation&quot;:&quot;0&quot;}\" data-image-title=\"image-1\" data-image-description=\"\" data-image-caption=\"\" data-medium-file=\"https:\/\/i0.wp.com\/magiteker.com\/wp-content\/uploads\/2023\/06\/image-1.png?fit=512%2C237&amp;ssl=1\" data-large-file=\"https:\/\/i0.wp.com\/magiteker.com\/wp-content\/uploads\/2023\/06\/image-1.png?fit=800%2C370&amp;ssl=1\" src=\"https:\/\/i0.wp.com\/magiteker.com\/wp-content\/uploads\/2023\/06\/image-1.png?resize=800%2C370&#038;ssl=1\" alt=\"\" class=\"wp-image-1404\" srcset=\"https:\/\/i0.wp.com\/magiteker.com\/wp-content\/uploads\/2023\/06\/image-1.png?w=800&amp;ssl=1 800w, https:\/\/i0.wp.com\/magiteker.com\/wp-content\/uploads\/2023\/06\/image-1.png?resize=512%2C237&amp;ssl=1 512w, https:\/\/i0.wp.com\/magiteker.com\/wp-content\/uploads\/2023\/06\/image-1.png?resize=768%2C355&amp;ssl=1 768w\" sizes=\"auto, (max-width: 800px) 100vw, 800px\" data-recalc-dims=\"1\" \/><\/figure>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Different data keywords can be used for a single class allowing for varied training data within a class. For example training two sets of images of different characters.<\/li>\n\n\n\n<li><strong>Important Note<\/strong>: Previous experiments have shown that without regularization images, or using images not generated by a model, training data will overwrite a model&#8217;s data damaging the models ability to generate images other than the training data.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>&#8211; Github README describing proper methods for constructing a dataset. According to the README Regularization images allow for prior preservation of a models existing dataset.<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","enabled":false}}},"categories":[21,67],"tags":[68,71,69],"class_list":["post-1386","post","type-post","status-publish","format-standard","hentry","category-code","category-stablediffusionai","tag-ai","tag-dreambooth","tag-stable-diffusion"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p6MIgq-mm","jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/posts\/1386","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/comments?post=1386"}],"version-history":[{"count":6,"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/posts\/1386\/revisions"}],"predecessor-version":[{"id":1409,"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/posts\/1386\/revisions\/1409"}],"wp:attachment":[{"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/media?parent=1386"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/categories?post=1386"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/tags?post=1386"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}