![](https://domain-seeger.de/wp-content/uploads/2022/10/DreamBooth0-1024x375.png)
![](https://domain-seeger.de/wp-content/uploads/2022/10/DreamBooth1-1024x506.png)
![](https://domain-seeger.de/wp-content/uploads/2022/10/DreamBooth2-1024x290.png)
![](https://domain-seeger.de/wp-content/uploads/2022/10/DreamBooth3-1024x463.png)
![](https://domain-seeger.de/wp-content/uploads/2022/10/DreamBooth4-1024x409.png)
Google presents DreamBooth, a technique to synthesize a subject (defined by 3-5 images) in new contexts defined by text input.
The method is based on Google’s pre-trained text-to-image model Imagen which is not publicly available. However, source code based on Stable Diffusion already exists on GitHub.
![](https://domain-seeger.de/wp-content/uploads/2022/10/DreamBooth5-1024x416.png)