diffusers VS Dreambooth-Stable-Diffusion

ShivamShrirao's Diffusers Pretrained diffusion models across multiple modalities.

Like the title say I'm trying to fine-tune a model to match a style of a popular manhwa. I'm using the ShivamShrirao Google Colab to accomplish this.

I am running the DreamBooth_Stable_Diffusion.ipynb notebook from ShivamShrirao locally on my machine. Let's say I have trained for 500 iterations and it hasn't converged yet. How do I make it resume training from that iteration so it can do another 500?

My understanding, based on messages from an (alleged) representative of colabs, is that the webui is the problem, not SD itself. This also seems to be the consensus in the comments section of other posts. I have not yet seen a link to colab based webui alternatives so here is something I found from a tutorial. I am certain that there are better alternatives. Anyone have a better idea? This will still probably be useful to other people like me who are just messing around.

I'm running ShivamShrirao's fork of diffusers; ran into a fp16 issue and had to patch in a fix from the main branch ( #1567 ).

I am running Shivam Stable Diffusion Jupyter notebook: diffusers/DreamBooth_Stable_Diffusion.ipynb at main · ShivamShrirao/diffusers · GitHub.

Are you using this one? https://github.com/S

Tons of stuff here, no? https://github.com/JoePenna/Dreambooth-Stable-Diffusion/

Joe Penna's Dreambooth (Tutorial|24GB) Most popular DB repo with great results.

1) The https://github.com/JoePenna/Dreambooth-Stable-Diffusion instructions say to use the 1.5 checkpoints - is that the latest? Can I use the 2+ models or?

I quickly turned to the second library, https://github.com/JoePenna/Dreambooth-Stable-Diffusion, because its readme was very encouraging, and its results were the best. Unfortunately, to use it on Colab, you need to sign up for Colab Pro to use advanced GPUs (at least 24GB of VRAM), and training a model requires at least 14 compute units. As a poor Chinese person, I could only buy Colab Pro from a proxy. The results from JoePenna/Dreambooth-Stable-Diffusion were fantastic, and the preparation was straightforward, requiring only <=20 512*512 photos without writing captions. I used it to create many beautiful photos.

I've found EveryDream to be brilliant and have switched from JoePenna's Dreambooth because I've found I get better results so long as I provide good captions for all the images, even if preparing the dataset takes 3x as long (took me 2 hours to crop and label the 54 images).

From what I know you can train with whatever size you want. But you need software that will support it. For example, ShivamShrirao/diffusers repo seems to allow a change of dimension. Also, you need HW that would support the training, because bigger images need more VRAM, for example,Joe Penna repo is using ~23GB with 512x512px so probably it's not a valid option. But the ShivamShrirao repo has optimizations that allow to run it with less VRAM.

This is a good starting place: https://github.com/JoePenna/Dreambooth-Stable-Diffusion