hlky

This is redundant. `compile_alt.py` deals with dynamic shape. There's no need to have dynamic batch support in `compile.py`. Also, this essentially reverts your changes from #755 and #765, `compile.py` previously...

Pix2pix PyTorch modules would need translating to AITemplate graph. ControlNet is available, refer to the documentation and code for further details. [compile_controlnet.py](https://github.com/facebookincubator/AITemplate/blob/main/examples/05_stable_diffusion/scripts/compile_controlnet.py) [compile_alt.py](https://github.com/facebookincubator/AITemplate/blob/main/examples/05_stable_diffusion/scripts/compile_alt.py)

AIT is not fully compatible with Diffusers, certain aspects of Diffusers related to Stable Diffusion have been implemented as AITemplate graph, there are block types etc that have not been...

@mzeynali It's unclear what you mean, inference step count is not involved in compilation.

If you see `demo.py` uses default 50 steps, you know how to change it :) `demo_alt.py` has `--steps` option. Yes it is possible to run different images as the batch,...

@mzeynali They are demos, they serve as a demonstration. There is nothing stopping you from using a demo in production, except common sense should tell you that is not ideal,...

`--width 512 512 --height 512 512` Not sure why you are doing this, the purpose of the alt scripts is to support dynamic shape. `stabilityai/stable-diffusion-v2` doesn't exist, I assume you...

> Are there any optimisations to get this running on a 8GB RTX 3060ti ? Reducing the size of the text array given to rank() decreases the vram usage These...

Having looked into this further it seems the core of the issue is with two different formats in the same repo. When the `parquet` config is first, the `WebDataset`s are...

Yes I am aware how the current estimator works, as stated in the issue this assumes a consistent file size across the entire set. There may not be a strict...