master-418-200cb6f

fix: avoid crash with VAE tiling and certain image sizes (#1090)

master-417-43a70e8

fix: add lora info to image metadata (#1086)

master-416-614f873

sync: update ggml (#1082)

master-415-d96b415

perf: optimize ggml_ext_chunk (#1084)

master-414-8f05f5b

feat: add support for custom scheduler (#694)

---------

Co-authored-by: leejet <leejet714@gmail.com>

master-413-15d0f82

feat(server): do not parse lora fromt client-side prompts (#1083)

master-412-6888fcb

feat: server add default_gen_params to override default args (#1050)

master-411-2aecdd5

feat: simple openai image generation api compatiple server (#1037)

master-410-11ab095

fix: resolve embedding loading issue when calling generate_image mult…

master-409-a3a88fc

fix: avoid crash loading LoRAs with bf16 weights (#1077)