Safe-and-Stable-Ckpt2Safetensors-Conversion-Tool-GUI VS EveryDream-trainer

Or just use this. https://github.com/diStyApps/Safe-and-Stable-Ckpt2Safetensors-Conversion-Tool-GUI

Alternately, this neat little gui can do it too. It does take up an additional gigabyte (due to dependencies), but it's fairly easy to use and can convert back to ckpt if needed.

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