Training Stable Diffusion Dreambooth on Multiple Subjects for Combined Image Generation

A look at training a Dreambooth model with 22 separate tokens in 9 datasets using image data from the 1960s Star Trek television series.

The model can generate each token separately, and in combination, for example, placing a character in a style-correct landscape, and maintains a film-like texture and coloration unless otherwise directed.

Shivam Shiraro's Dreambooth code:

WinHTTrack/WebHTTrack:

[Willtry-lg]

Thank you for your videos😊
Can I know if, when we have 5 pictures for each of two different subject(assume a1 person and a2 person), using stable diffusion can we generate these tree situation in one model? 1.a1 person in different background
2. a2 person in different backgrounds
3. a1 and a2 in the same image with different background .
Do I need to create 3 model for that task?
How to do that type of task ?

[miladaghajohari]

Hey, great. But you did not produce images that contain two concepts at the same time, did you?

[alphadevilll]

Bro can you please make a tutorial on how to train a model with cartoony landscapes or living spaces (for eg a southpark like 2d scenery, a living room, kitchen etc )

[omkar]

Can you do this for beginners, like how to make folders for different image set and training to stable diffusion on Google colab

[MattHabermehl]

What is the result of having only one sample prompt per checkpoint?

[nikgrid]

Is it possible to download your awesome Star Trek Model please?