DREAMBOOTH: Train MULTIPLE Subjects In Stable Diffusion At The Same Time For FREE!

With the recent development in AI technology and training, you can now use Dreambooth (based on a Google’s AI) to train a stable diffusion model with multiple subjects (people, style, objects) using your own images and all of that for Free! So in this video, I will show you what you need to do before training, any tips and tricks you need to know before you can train multiple subjects in one go. This will allow you to have multiple people trained on one single Ckpt file in less than an hour!

Did you manage to train multiple people or style? Let me know in the comments!
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
SOCIAL MEDIA LINKS!
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

Special thanks to Royal Emperor:
- DanO..

Thank you so much for your support on Patreon! You are truly a glory to behold! Your generosity is immense, and it means the world to me. Thank you for helping me keep the lights on and the content flowing. Thank you very much!

#stablediffusion #dreambooth #stablediffusiontutorial
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
WATCH MY MOST POPULAR VIDEOS:
RECOMMENDED WATCHING - My "Stable Diffusion" Playlist:

RECOMMENDED WATCHING - My "Tutorial" Playlist:

Disclosure: Bear in mind that some of the links in this post are affiliate links and if you go through them to make a purchase I will earn a commission. Keep in mind that I link these companies and their products because of their quality and not because of the commission I receive from your purchases. The decision is yours, and whether or not you decide to buy something is completely up to you.

[Aitrepreneur]

HELLO HUMANS! Thank you for watching & do NOT forget to LIKE and SUBSCRIBE For More Ai Updates. Thx <3
"K" - Your Ai Overlord

[dreamzdziner]

I was wandering around 'dreambooth fast colab' for few days not knowing how to start. Was waiting for this exact video. Thank you so much dear AI Overlord❤🙏🏽

[amj]

Just tested this and it's much better than before, I'm getting really good results on the model I trained. Thanks for letting us know about this Aitrepreneur

[tungstentaco]

Just tried this. Worked great! Definitely the easiest colab dreambooth method so far. Thanks!
FYI. I ran 4500 steps with checkpoint saved every 500 steps and was getting close to the hardrive space limit on my google colab session. So something to keep an eye on if you run a lot of steps in your training.

[IbycusCrane]

Thanks! Please let us know when we can use this locally!

[Voidgamer]

Fantastic, I"ve Been waiting for something like this to train artistic styles, and once again K your Tutorials are simple, straightforward, and easy to follow! Your Number#1! at this! Colab should hire you to do their training videos.

[alinasama]

since the update on this colab, could you please explain some new settings on that? like text encoder settings or UNet_Training_Steps settings? Thank you so much!

[IlRincreTeam]

I started using again the Dreambooth thing yesterday and found there the multiple concept training... too scared to try it out, perfect timing as usual Mr. K!

[Ms.Aquarelle]

I've found that if you have the steps too high it can lead to the influence of the source images being too strong where it'll pretty much ignore your prompt altogether. I've found success at increasing the input images to around 70 but keeping steps at 2000 whereas using 3000 steps and 30 images led to the issue mentioned earlier. I'm still playing around with it so I'm not sure about the sweet spot of steps vs image count, and it may just differ depending on the input images.

[MALprocrastina]

I was looking forward to this video to see where I went wrong and I think it was by running the old version as well, it put everything together and created a new face that was a mix of all the photos.

Thanks for these videos 😃

[magichourai]

What prompts do you use to get both subjects to show up in the same image?

[alonsorojas]

Amazing, thanks for the information and constant updates. This changes so fast! Will you consider making a video about sampling methods?

[RandallMadrigal]

Hi Aitrepreneur, thanks so much. After training two or more characters or styles, could you retrain another on the same cptk? without affecting the terms already set.

[jankownacki]

Now it would be greate to be able to do it for more subjects locally! :D

[nelson]

Hi Aitrepreneur, thanks for your sharing!! I have trained a person and two hats, I fed in 20 images per class. In short, the human performance is perfect, but hats are not doing so great. Is there any params need to setup for training an non-human object?

[VaisakhBsonline]

Hi, it seems the dream booth notebook has been updated and I find it hard on the model download section. it's asking path to hugging face and model. I googled but nothing worked. can you please help?

[ericruffy]

have this tested, yet another quick way to train, directly to cpkt, 12~18 photos should be enough and even 9 photos with *100=900 steps 're acceptable! might say, this is CRAZY. (you know how much time 900 steps should take...) far beyond the imagination before giving this a try, thanks Overlord, it's overload (😁)

[leafdriving]

Aitrepreneur - use a photoshop equivelent to paste your "person to be changed" beside someone wearing the "change", then inpaint out the "person to be changed" stuff you want changed- prompt they are identical twins - mind blowing

[moviecontext]

9:50 same feeling, thanks for your contribution <3, aloha from Perú

[canaldetestes]

Hi @Aitrepreneur, thank you very much for this video, also for the tips.