It works with as few as 3-5 custom images. For example, you can train the Stable Diffusion v1.5 with an additional dataset of vintage cars to bias the aesthetic of cars towards the sub-genre.ĭreambooth, developed by Google, is a technique to inject custom subjects into text-to-image models. They both start with a base model like Stable Diffusion v1.5.Īdditional training is achieved by training a base model with an additional dataset you are interested in. The two main fine-tuning methods are (1) Additional training and (2) Dreambooth. Instead of tinkering with the prompt, you can use a custom model that is fine-tuned with images of that sub-genre. However, it could be difficult to generate images of a sub-genre of anime. For example, it generates anime-style images with the keyword “anime” in the prompt. The Stable diffusion base model is great but is not good at everything. Why do people make Stable Diffusion models? It generates anime-style images by default. For example, the Anything v3 model is trained with anime images.
It takes a model that is trained on a wide dataset and trains a bit more on a narrow dataset.Ī fine-tuned model tends to generate images similar to those used in the training. Why do people make Stable Diffusion models?įine-tuning is a common technique in machine learning.