Make lora loading api endpoint functional

Improve lora implementation

Add lora loading

Move compile out of FluxPipeline init

Dynamic swap with cublas linear / optional improved precision with vram drawback

Allow overriding config values from load_pipeline_from_config_path

Add case where seed is string & try/catch if invalid

Remove unnecessary synchronize, add more universal seeding & limit if run on windows

Remove unnecessary code, hide prints behind debug flag, hide warnings

Adding device specific configs & more input image type options + small model spec from args change

Add fields to configs, fix issue with offload from bnb, remove extra random text code

Fix non-offload inference & add option to load from prequantized flux

Add offloading & improved fp8 inference.

Updates..

Add img2img, more options, gradio interface