14 Commits

Author	SHA1	Message	Date
Brandon Rising	5f59a828f9	Setup flux model loading in the UI	2024-08-26 20:17:50 -04:00
Ryan Dick	1fa6bddc89	WIP on moving from diffusers to FLUX	2024-08-26 20:17:50 -04:00
Ryan Dick	f01f56a98e	LLM.int8() quantization is working, but still some rough edges to solve.	2024-08-26 20:17:50 -04:00
Ryan Dick	99b0f79784	Clean up NF4 implementation.	2024-08-26 20:17:50 -04:00
Ryan Dick	e1eb104345	NF4 inference working	2024-08-26 20:17:50 -04:00
Ryan Dick	a52c899c6d	Split a FluxTextEncoderInvocation out from the FluxTextToImageInvocation. This has the advantage that we benfit from automatic caching when the prompt isn't changed.	2024-08-26 20:17:50 -04:00
Ryan Dick	eeabb7ebe5	Make quantized loading fast for both T5XXL and FLUX transformer.	2024-08-26 20:17:50 -04:00
Ryan Dick	3cf0365a35	Make float16 inference work with FLUX on 24GB GPU.	2024-08-26 20:17:50 -04:00
Ryan Dick	5870742bb9	Add support for 8-bit quantizatino of the FLUX T5XXL text encoder.	2024-08-26 20:17:50 -04:00
Ryan Dick	01d8c62c57	Make 8-bit quantization save/reload work for the FLUX transformer. Reload is still very slow with the current optimum.quanto implementation.	2024-08-26 20:17:50 -04:00
Ryan Dick	55a242b2d6	Minor improvements to FLUX workflow.	2024-08-26 20:17:50 -04:00
Ryan Dick	45263b339f	Got FLUX schnell working with 8-bit quantization. Still lots of rough edges to clean up.	2024-08-26 20:17:50 -04:00
Ryan Dick	3319491861	Use the FluxPipeline.encode_prompt() api rather than trying to run the two text encoders separately.	2024-08-26 20:17:50 -04:00
Ryan Dick	b39031ea53	First draft of FluxTextToImageInvocation.	2024-08-26 20:17:50 -04:00