feat: add support for Chroma Radiance x0 (#1091)

* Add x0 Flux pred (+prepare for others)

* Fix convert models with empty tensors

* patch_32 exp support attempt

* improve support for patch_32

* follow official pipeline

---------

Co-authored-by: leejet <[email protected]>

chore: give feedback about cfg values smaller than 1 (#1088)

feat: default to LCM scheduler for LCM sampling (#1109)

* feat: default to LCM scheduler for LCM sampling

* fix bug and attempt to get default scheduler for vid_gen when none is set

---------

Co-authored-by: leejet <[email protected]>

feat: add KL Optimal scheduler (#1098)

chore: remove unused debug code

fix: make flash attn work with high noise diffusion model (#1111)

refactor: optimize the printing of version log (#1102)

feat: supports correct UTF-8 printing on windows (#1101)

feat: add taehv support for Wan/Qwen  (#937)

fix: added a clean exit in ModelLoader::load_tensors if OOM  (#1097)