feat: add more built-in highres upscalers (#1456)

feat: add sd-webui style Hires. fix support (#1451)

feat: support safetensors export in convert mode (#1444)

feat: add restricted torch legacy checkpoint loading (#1443)

refactor: move model file IO into dedicated module (#1442)

fix: correct image to image DDIM and TCD (#1410)

feat: adapt LCM for flow models (#1413)

chore: enable MSVC parallel compilation with /MP (#1438)

ci: skip docker image build job on pull requests (#1439)

feat(server): implement vid_gen async API and mode-aware capabilities (…

…#1437)