master-332-0723ee5

refactor: optimize option printing (#900)

master-331-90ef5f8

feat: add auto-resize support for reference images (was Qwen-Image-Ed…

master-330-db6f479

feat: add wtype stat (#899)

master-326-40a6a87

fix: resolve precision issues in SDXL VAE under fp16 (#888)

* fix: resolve precision issues in SDXL VAE under fp16

* add --force-sdxl-vae-conv-scale option

* update docs

master-325-e370258

feat: added prediction argument (#334)

master-324-a7d6d29

chore: allow building ggml as a separate shared lib (#468)

master-323-2e9242e

feat: add Qwen Image Edit support (#877)

* add ref latent support for qwen image

* optimize clip_preprocess and fix get_first_stage_encoding

* add qwen2vl vit support

* add qwen image edit support

* fix qwen image edit pipeline

* add mmproj file support

* support dynamic number of Qwen image transformer blocks

* set prompt_template_encode_start_idx every time

* to_add_out precision fix

* to_out.0 precision fix

* update docs

master-322-c64994d

fix: better progress display for second-order samplers (#834)

master-321-5436f6b

fix: correct canny preprocessor (#861)

master-320-1c32fa0

fix: avoid generating black images when running T5 on the GPU (#882)