{"id":733,"date":"2023-04-14T04:45:04","date_gmt":"2023-04-14T04:45:04","guid":{"rendered":"https:\/\/ai-box.eu\/?p=733"},"modified":"2023-04-15T05:09:59","modified_gmt":"2023-04-15T05:09:59","slug":"stable-diffusion-dreambooth-training-finetuning-run-part-2-2","status":"publish","type":"post","link":"https:\/\/ai-box.eu\/en\/top-story-en\/stable-diffusion-dreambooth-training-finetuning-run-part-2-2\/733\/","title":{"rendered":"Stable Diffusion – Dreambooth Training Finetuning Run Part 2\/2"},"content":{"rendered":"

After you have added the Dreambooth extension to your AUTOMATIC1111 system, I would like to briefly explain how to set up and start a training. Since I’m still learning and trying out myself, this tutorial should be understood as a first idea of how the processes are and what you have to pay attention to. Surely I will add to this guide from time to time or correct it when I have more knowledge and experience. But for a first start and to get a feeling how complex the whole thing is I hope that the description helps you to train a first own net that also shows something, i.e. can generate via a prompt what you have trained on top of the existing net.<\/p>\n

Again it is important to have a good NVIDIA GPU in your computer so that the training or this small project is fun. I always recommend the 30XX series or even higher performance. I use an NVIDIA A6000 in my computer and am quite satisfied with the speed. Probably an RTX 4090 would already be faster again. But I do not have a comparison.<\/p>\n

Note:<\/strong> This article is currently a documentation for me how I have fine-tuned the model. I will keep updating the article as I learn more.<\/p>\n

\n
\n

Table of Contents<\/p>\nToggle<\/span><\/path><\/svg><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n