Add StableDiffusion Dreambooth example

[0xdevalias]

Currently there are StableDiffusion examples here:

• https://github.com/facebookincubator/AITemplate/tree/main/examples/05_stable_diffusion

But it would be awesome if there was also examples of using this for Dreambooth:

• https://dreambooth.github.io/
• https://github.com/huggingface/diffusers/tree/main/examples/dreambooth

See also:

• https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/1625
• https://github.com/TheLastBen/fast-stable-diffusion/issues/73
• https://github.com/ShivamShrirao/diffusers/issues/32

And similar end-goal but these aren't based on AITemplate:

• https://github.com/hpcaitech/ColossalAI/issues/1935
• https://github.com/huggingface/diffusers/issues/1212
• https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/4606
• https://github.com/d8ahazard/sd_dreambooth_extension/issues/174
• https://github.com/TheLastBen/fast-stable-diffusion/issues/493
• https://github.com/ShivamShrirao/diffusers/issues/129

[0xdevalias]

AITemplate is for inference. I don't think it would provide any speedup during training. EDIT: nevermind. You can still accelerate the frozen parts of the model.

Originally posted by @matteoserva in https://github.com/ShivamShrirao/diffusers/issues/32#issuecomment-1275067312

It is just for inference so won't be helpful in training. I also tested it, it's good for inference but also takes a really long time to compile.

Originally posted by @ShivamShrirao in https://github.com/ShivamShrirao/diffusers/issues/32#issuecomment-1279625711

[chenyang78]

It is just for inference so won't be helpful in training. I also tested it, it's good for inference but also takes a really long time to compile.

Just FYI - The compilation time with the latest open-source version has been improved a lot from our first release. In our experiences, it can be 4X faster for the models where computation-intensive ops are mostly GEMM-family ops. We've made similar improvement for Conv ops in our internal version, which will be sync-ed to the open-source repo later. Stay tuned. Thanks.