CalamitousFelicitousness 6123655ac2 LoRA load Torch tuple and string version checking ...

Due to BitsandBytes trying to use tuple and comparison to check Torch version which is given as a string, using LoRA with a quantized model results in a TypeError. This commit adds support for both.

2025-08-13 23:39:18 +01:00

..

extra_networks_lora.py

major refactor: remove backend original

2025-07-05 13:16:46 -04:00

lora_apply.py

SDNQ move non_blocking to quant config

2025-08-11 15:07:02 +03:00

lora_common.py

lora modularize code

2025-04-01 13:39:47 -04:00

lora_convert.py

Preliminary support for sd1.5/sdxl OMI lora

2025-04-27 16:53:22 -05:00

lora_extract.py

major refactor: remove backend original

2025-07-05 13:16:46 -04:00

lora_load.py

LoRA load Torch tuple and string version checking

2025-08-13 23:39:18 +01:00

lora_nunchaku.py

nunchaku lora support

2025-04-17 11:45:37 -04:00

lora_overrides.py

add /sdapi/v1/network

2025-08-10 10:53:28 -04:00

lora_timers.py

yet another lora refactor

2024-12-09 13:40:19 -05:00

lyco_helpers.py

lora-refactor

2024-12-01 10:54:51 -05:00

network_full.py

Major lora refactor: works on my machine edition

2024-11-23 21:57:03 -06:00

network_glora.py

Major lora refactor: works on my machine edition

2024-11-23 21:57:03 -06:00

network_hada.py

Major lora refactor: works on my machine edition

2024-11-23 21:57:03 -06:00

network_ia3.py

Major lora refactor: works on my machine edition

2024-11-23 21:57:03 -06:00

network_lokr.py

Major lora refactor: works on my machine edition

2024-11-23 21:57:03 -06:00

network_lora.py

lint

2025-07-29 09:24:23 -04:00

network_norm.py

lint fixes

2024-11-29 08:01:26 -05:00

network_oft.py

lint fixes

2024-11-29 08:01:26 -05:00

network.py

major refactor: remove backend original

2025-07-05 13:16:46 -04:00

networks.py

lora restore weights to orig device on apply

2025-04-07 07:49:18 -04:00