x-stable-diffusion VS sd_dreambooth_extension

Cheapest would be to deploy it on your own using: https://github.com/stochasticai/x-stable-diffusion. Let me if you need more help on real-time inference.

However, I suggest you "accelerate" your inference first. For example, you can use open-source inference engines (see: https://github.com/stochasticai/x-stable-diffusion) to easily accelerate your inference 2x or more. That means you can generates 2x more images / $ on public clouds.

Brilliant, the x-stable-diffusion TensorRT/ AITemplate etc. sample image suggested they weren't consistent between the optimizations at all, unless they hadn't locked the seed which would have been foolish for the test.

I was looking at this three days ago, the problem is there seems to be a huge difference in what is being generated looking at the example spread on https://github.com/stochasticai/x-stable-diffusion , whereas copying model, params, seed should be giving a near identical image.

I am trying to use StableDiffusion via AUTOMATIC1111 with the Dreambooth extension

When I first attempted SD training, I was very frustrated. It wasn't until I found this obscure forum thread on Github that I actually started producing great results with Dreambooth. Because I have such satisfactory results, I'm very reluctant to beat my brains against LoRa and its related training techniques. I gave up trying to train TI embeddings a long time ago. And I never figured out how to train or how to use hypernetworks. I've only been able to get good results with Dreambooth directly because of that thread I linked above. I make LoRas by extracting them from Dreambooth-trained checkpoints. And I have no idea if I'm doing the extractions the right way or not.

Getting the same with automatic1111 and sd_dreambooth extension. Check out more here in the issues log: https://github.com/d8ahazard/sd_dreambooth_extension/issues/1266

It's several moths old and many things have changed. But the spreadsheet available through this thread on Github has been indispensable for me when I train Dreambooth models. I'm astounded no one talks about it. I bring it up all the time. The research presented there should be continued. I'd love to see similar research done for SD v2.1.

Training rate is paramount. Read this Github thread.

https://github.com/d8ahazard/sd_dreambooth_extension/discussions/547/ (in depth training principles understanding)

sd_dreambooth_extension https://github.com/d8ahazard/sd_dreambooth_extension.git main 926ae204 Fri Mar 31 15:12:45 2023 unknown

also the Dreambooth extension supports API (https://github.com/d8ahazard/sd_dreambooth_extension/blob/main/scripts/api.py) so i'm not sure where do you get those news :/