StableTuner VS EveryDream-trainer

Of all dreamboothing/finetuning implementations I tried I liked StableTuner the most. Might be worth giving it a shot to compare as well.

Largest I've gone is about 100 images for objects or people. I don't think it matters though, it can be a hassle setting up and resuming the training session each time if your doing small sessions. Stable Tuner can simplify all of this by helping you set everything up through their client installed locally. You can then easily do your training locally in short sessions or have it automatically packed up to be exported to colab or another gpu hosting service, also with the ability to train in short sessions. Its a smart way to manage large training projects like yours. It requires a bit of time setting up but most folks who have already played around with dreambooth should be able to navigate their way through easily enough. It has all the other training methods built into it too, including proper fine tuning https://github.com/devilismyfriend/StableTuner

Some people also like StableTuner: https://github.com/devilismyfriend/StableTuner

Stable Tuner seems like it's setup to allow training on regular/inpaint/depth models. https://github.com/devilismyfriend/StableTuner

StableTuner is an alternative to the sd_dreambooth plugin. It can do Dreambooth and Fine Tuning (I haven't tried this but I think it's embeddings) It uses diffusers but will convert between that and ckpt files, is for Windows/Nvidia, and uses a local app instead of a webapp. This is the only successful local Dreambooth I've done. You'll need to go to their discord for help but it's not hard to use.

Dreambooth is has better results in older commits. StableTuner is better for training : https://github.com/devilismyfriend/StableTuner

https://github.com/victorchall/EveryDream-trainer Haven't tried it myself.

In terms of training, you've got some really good links and comments to youtube tutorials, but if you're interested in more information about finetuning a model (as opposed to training from scratch), this is a good repo that has a lot of tools for finetuning, including an auto-captioner using BLIP and automatic file renaming. This is the actual finetuning repo.

Every Dream Trainer: Is basically a Dreambooth combine with Fine Tunning, so you can train multiples thing and a lot images: https://github.com/victorchall/EveryDream-trainer

If you have the GPU for it, I'd recommend training all three things at once with (for example) https://github.com/victorchall/EveryDream-trainer. It recommends using "ground truth" training images - i.e. images from LAION-5B, which Stable Diffusion was originally trained with to have better prior preservation (retaining the flexibility of the original model) while incorporating new concepts, potentially even several different concepts in a single training run.

I used about 300 captioned images (mainly beautiful MJ stuff), and used https://github.com/victorchall/EveryDream-trainer on RunPod for finetuning

SD 1.5 512x512 model for making christmas style cookies of whatever you'd like. trained on 30 512x512 images with manual captions in everydream

This is the good one: https://github.com/victorchall/EveryDream-trainer