![]() ![]() It’s recommended that you provide ~50 images of what you’d like to train Stable Diffusion on to get great results.On the other hand, if you want it in the generated images, make sure it’s in your pictures more often. If you want to avoid seeing that element in your generated image, make sure not to repeat it in every shot. This can apply to anything, like jewelry, clothes, or even people in the background. For example, if you take multiple pictures with the same green field behind you, it’s likely that the generated images of you will also contain the green field, even if you want a dystopic background. When generating new images, whatever you capture will be over-represented.Showing a variety of expressions and emotions.Taking pictures on different days, in different lighting conditions, and with different backgrounds. ![]() Try to change things up as much as possible in each picture.If you’re uploading images of a person, try something like 70% close-ups, 20% from the chest up, 10% full body, so Stable Diffusion also gets some idea of the rest of the subject and not only the face. Upload a variety of images of your subject.When choosing images, it’s recommended to keep the following in mind to get the best results: Check tl dr AI News Use DreamBooth to Fine-Tune Stable Diffusion in Google Colab Prepare Images Choosing Images We cover the latest news and tutorials in the AI art world on a daily basis, so that you can stay up-to-date with the latest developments. In this newsletter we distill the information that’s most valuable to you into a quick read to save you time. We set up a newsletter called tl dr AI News. Sidenote: AI art tools are developing so fast it’s hard to keep up. Ideally, you should use more images to get better results. In this example, I’m finetuning it using 20 images of the Sandman from The Sandman (TV Series) and ~20 images of Aemond Targaryen from House of the Dragon. This is a quick video of me fine-tuning Stable Diffusion with DreamBooth from start to finish. If You Just Trained a Model but Didn’t Get to Test It Because of an Error.ImportError: cannot import name ‘VectorQuantizer2’.ModuleNotFoundError: No module named ‘modules.hypernetworks’.Upload Your Trained Model to Hugging Face.Test the Trained Model (with Stable Diffusion WebUI by AUTOMATIC1111).Input Hugging Face Token and Run Third Cell to Download Stable Diffusion.Run Second Cell to Set up The Environment.Open Fast Stable Diffusion DreamBooth Notebook in Google Colab.Use DreamBooth to Fine-Tune Stable Diffusion in Google Colab. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |