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
..
forge_canvas	upgrade js canvas for #881	2024-07-28 08:07:37 -06:00
alter_samplers.py	rename file	2024-08-03 15:51:04 -07:00
bnb_installer.py	forge 2.0.0	2024-08-10 19:24:19 -07:00
config.py	upload meta files	2024-08-18 00:12:53 -07:00
cuda_malloc.py	add two optimizations	2024-02-23 18:39:32 -08:00
diffusers_patcher.py	move to new backend - part 2	2024-08-03 15:10:37 -07:00
forge_space.py	change space path order	2024-08-18 23:55:28 -07:00
forge_version.py	Update forge_version.py	2024-08-10 19:58:04 -07:00
gradio_compile.py	integrate latent modifier	2024-02-09 14:38:57 -08:00
initialization.py	Forge Space and BiRefNet	2024-08-17 08:29:08 -07:00
main_entry.py	Implement some rethinking about LoRA system	2024-08-19 04:31:59 -07:00
main_thread.py	thread safety	2024-08-13 15:45:45 -07:00
patch_basic.py	Forge Space and BiRefNet	2024-08-17 08:29:08 -07:00
shared_options.py	Not all AUTOMATIC have beard	2024-08-15 01:25:47 -07:00
shared.py	move to new backend - part 2	2024-08-03 15:10:37 -07:00
supported_controlnet.py	revise structure	2024-08-07 20:44:34 -07:00
supported_preprocessor.py	rename files	2024-08-03 15:54:39 -07:00
utils.py	add note to Tiling	2024-08-08 13:33:03 -07:00