{"id":1382,"date":"2023-06-21T09:27:59","date_gmt":"2023-06-21T03:27:59","guid":{"rendered":"http:\/\/magiteker.com\/?p=1382"},"modified":"2023-06-21T09:36:02","modified_gmt":"2023-06-21T03:36:02","slug":"resource-training-stable-diffusion-with-dreambooth","status":"publish","type":"post","link":"https:\/\/magiteker.com\/index.php\/2023\/06\/21\/resource-training-stable-diffusion-with-dreambooth\/","title":{"rendered":"Resource: Training Stable Diffusion with Dreambooth"},"content":{"rendered":"\n<p>&#8211;<a href=\"https:\/\/huggingface.co\/blog\/dreambooth\">Blog Post<\/a><\/p>\n\n\n\n<p>This article describes experiments with different Learning Rates in training models using Dreambooth.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><a href=\"https:\/\/huggingface.co\/blog\/dreambooth#summary-of-initial-results\"><\/a> FTA: Summary of Initial Results<\/h3>\n\n\n\n<p>To get good results training Stable Diffusion with Dreambooth, it&#8217;s important to tune the learning rate and training steps for your dataset.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>High learning rates and too many training steps will lead to overfitting. The model will mostly generate images from your training data, no matter what prompt is used.<\/li>\n\n\n\n<li>Low learning rates and too few steps will lead to underfitting: the model will not be able to generate the concept we were trying to incorporate.<\/li>\n<\/ul>\n\n\n\n<p>Faces are harder to train. In our experiments, a learning rate of <code>2e-6<\/code> with <code>400<\/code> training steps works well for objects but faces required <code>1e-6<\/code> (or <code>2e-6<\/code>) with ~1200 steps.<\/p>\n\n\n\n<p>Image quality degrades a lot if the model overfits, and this happens if:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>The learning rate is too high.<\/li>\n\n\n\n<li>We run too many training steps.<\/li>\n\n\n\n<li>In the case of faces, when no prior preservation is used, as shown in the next section.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>&#8211;Blog Post This article describes experiments with different Learning Rates in training models using Dreambooth. FTA: Summary of Initial Results To get good results training Stable Diffusion with Dreambooth, it&#8217;s important to tune the learning rate and training steps for your dataset. Faces are harder to train. In our experiments, a learning rate of 2e-6 [&hellip;]<\/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-1382","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-mi","jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/posts\/1382","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=1382"}],"version-history":[{"count":3,"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/posts\/1382\/revisions"}],"predecessor-version":[{"id":1385,"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/posts\/1382\/revisions\/1385"}],"wp:attachment":[{"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/media?parent=1382"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/categories?post=1382"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/magiteker.com\/index.php\/wp-json\/wp\/v2\/tags?post=1382"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}