You might have seen a few YouTube videos of mine under *MysteryGuitarMan*. I'm now a feature film director. You might have seen [ARCTIC](https://www.youtube.com/watch?v=N5aD9ppoQIo&t=6s) or [STOWAWAY](https://www.youtube.com/watch?v=A_apvQkWsVY).
For my movies, I need to be able to train specific actors, props, locations, etc. So, I did a bunch of changes to @XavierXiao's repo in order to train people's faces.
I can't release all the tests for the movie I'm working on, but when I test with my own face, I release those on my Twitter page - [@MysteryGuitarM](https://twitter.com/MysteryGuitarM).
Lots of these tests were done with a buddy of mine -- Niko from CorridorDigital. It might be how you found this repo!
I'm not really a coder. I'm just stubborn, and I'm not afraid of googling. So, eventually, some really smart folks joined in and have been contributing. In this repo, specifically: @djbielejeski@gammagec@MrSaad–– but so many others in our Discord!
- If, like myself, you don't happen to own one of those, I'm including a Jupyter notebook here to help you run it on a rented cloud computing platform.
- Best practice is to change the token to a celebrity name. Here's [my wife trained with the exact same settings, except for the token](#using-the-generated-model)
- You will want to increase your disk space, and filter on GPU RAM (12gb checkpoint files + 4gb model file + regularization images + other stuff adds up fast)
If you trained with `joepenna` under the class `person`, the model should only know your face as:
```
joepenna person
```
Example Prompts:
🚫 Incorrect (missing `person` following `joepenna`)
```
portrait photograph of joepenna 35mm film vintage glass
```
✅ This is right (`person` is included after `joepenna`)
```
portrait photograph of joepenna person 35mm film vintage glass
```
You might sometimes get someone who kinda looks like you with joepenna (especially if you trained for too many steps), but that's only because this current iteration of Dreambooth overtrains that token so much that it bleeds into that token.
---
#### ☢ Be careful with the types of images you train
While training, Stable doesn't know that you're a person. It's just going to mimic what it sees.
So, if these are your training images look like this:
You're only going to get generations of you outside next to a spiky tree, wearing a white-and-gray shirt, in the style of... well, selfie photograph.
Instead, this training set is much better:
The only thing that is consistent between images is the subject. So, Stable will look through the images and learn only your face, which will make "editing" it into other styles possible.
## Oh no! You're not getting good generations!
#### <a name="they-dont-look-like-you"></a> OPTION 1: They're not looking like you at all! (Train longer, or get better training images)
#### <a name="they-sorta-look-like-you-but-exactly-like-your-training-images"></a> OPTION 2: They're looking like you, but are all looking like your training images. (Train for less steps, get better training images, fix with prompting)
#### <a name="they-look-like-you-but-not-when-you-try-different-styles"></a> OPTION 3: They're looking like you, but not when you try different styles. (Train longer, get better training images)
Dreambooth is now supported in Hugging Face diffusers for training with stable diffusion, try it out in the colab:
[](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb)
