[enhancement]: support Flex.1

### Is there an existing issue for this?

- [x] I have searched the existing issues

### What should this feature add?

ostris's [Flex.1-alpha](https://huggingface.co/ostris/Flex.1-alpha):
> Flex.1 alpha is a pre-trained base 8 billion parameter rectified flow transformer capable of generating images from text descriptions. It has a similar architecture to [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev), but with fewer double transformer blocks (8 vs 19). It began as a finetune of [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) which allows the model to retain the Apache 2.0 license.

Despite the fact that its model card says "The model can be used almost identically to FLUX.1-dev and will work out of the box with most inference engines that support that. (Diffusers, ComfyUI etc.)", it doesn't work out of the box with current Invoke.

### Additional Content

Ryan started looking at this already: https://github.com/invoke-ai/InvokeAI/compare/main...ryan/flex-1-alpha