5 Commits

Author	SHA1	Message	Date
layerdiffusion	d38e560e42	Implement some rethinking about LoRA system ... 1. Add an option to allow users to use UNet in fp8/gguf but lora in fp16. 2. All FP16 loras do not need patch. Others will only patch again when lora weight change. 3. FP8 unet + fp16 lora are available (somewhat only available) in Forge now. This also solves some “LoRA too subtle” problems. 4. Significantly speed up all gguf models (in Async mode) by using independent thread (CUDA stream) to compute and dequant at the same time, even when low-bit weights are already on GPU. 5. View “online lora” as a module similar to ControlLoRA so that it is moved to GPU together with model when sampling, achieving significant speedup and perfect low VRAM management simultaneously.	2024-08-19 04:31:59 -07:00
lllyasviel	a07c758658	intergrate k-diffusion	2024-08-07 15:05:42 -07:00
layerdiffusion	b7878058f9	improve backward combability #936	2024-08-06 01:06:24 -07:00
layerdiffusion	0863765173	rework sd1.5 and sdxl from scratch	2024-08-05 03:08:17 -07:00
layerdiffusion	bb5083f3c2	rework sample function	2024-08-03 13:27:23 -07:00