[enhancement]: support Flex.1

[keturn]

Is there an existing issue for this?

• [x] I have searched the existing issues

What should this feature add?

ostris's 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, but with fewer double transformer blocks (8 vs 19). It began as a finetune of 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