17 Commits

Author	SHA1	Message	Date
filipstrand	96848e320f	Add support for multiple LoRAs again	2024-09-05 19:54:46 +02:00
filipstrand	ff9f998638	Small fixes	2024-09-04 23:16:02 +02:00
filipstrand	f28fffe0cf	Point out the .safetensors file again	2024-09-04 22:44:11 +02:00
filipstrand	a3567bddd7	Start supporting only single LoRA (and some other simplifications)	2024-09-04 22:15:03 +02:00
filipstrand	6d35db5e9a	Use mx.load instead of safe_open	2024-09-04 21:05:19 +02:00
filipstrand	5ad5352481	Introduce weight util for shared methods	2024-09-04 20:20:27 +02:00
filipstrand	af41b08d90	Move LoRA related things to a LoraUtil (have to think about where to best place this later...)	2024-09-04 20:10:45 +02:00
filipstrand	8983070728	Code style improvements and some restructuring	2024-09-04 20:10:45 +02:00
Filip Strand	b4c27a6fab	raise error if layer cannot be loaded ... Co-authored-by: Fabio Peruzzo <39661245+Xuzzo@users.noreply.github.com>	2024-09-04 19:43:32 +02:00
elitexp	0fd03c7552	@Xuzzo - Weight Adjustment as Original Transformer ... Co-authored-by: Fabio Peruzzo <39661245+Xuzzo@users.noreply.github.com>	2024-09-04 21:52:51 +05:45
Sujip Maharjan	8d8812675e	feat: --apply-lora a.safetensors b.safetensors c.safetensor --lora-scales 0.5 1.0 0.5	2024-09-03 19:36:15 +05:45
Sujip Maharjan	03b929e732	feat: Add --lora-scale parameter to adjust the scaling of LoRA weights	2024-09-03 18:39:01 +05:45
elitexp	4dfb3aa892	Clean up weight handler ... @xuzzo Cleanup code Co-authored-by: Fabio Peruzzo <39661245+Xuzzo@users.noreply.github.com>	2024-09-03 18:19:21 +05:45
Sujip Maharjan	f82caa3298	Icrecream dependency removed, not required -- error	2024-09-03 13:16:35 +05:45
Sujip Maharjan	cd54ad137c	Apply lora with --apply-lora <path-to-safetensors>	2024-09-03 07:38:04 +05:45
filipstrand	fdc4cb9892	Rewrite weight handling and add quantization support	2024-08-30 22:13:36 +02:00
filipstrand	7a277fc326	Rename flux_1_schnell folder to flux_1	2024-08-20 22:37:32 +02:00