v2.2.2

Version 2.2.2

What's Changed

• fix: Handle missing lora IDs by @db0 in #116
• fix: more graceful civitai lora handling by @tazlin in #117

Full Changelog: v2.2.1...v2.2.2

v2.2.1

Version 2.2.1

What's Changed

• feat: update to comfy version e13454 (SDV support; version as of Dec 6 2023) by @tazlin in #114
• feat: update to comfy version e13454 (SDV support) by @tazlin in #115

Full Changelog: v2.2.0...v2.2.1

v2.2.0

Version 2.2.0

What's Changed

• feat: Inference and PP return objects instead of Images by @db0 in #96
• chore: add dependabot support by @tazlin in #97
• build(deps): bump the python-packages group with 6 updates by @dependabot in #98
• fix: don't count tainted models as available by @tazlin in #99
• fix: allow success messages (level 25) to show at verbosity 2 by @tazlin in #109
• feat: return metadata about generations (succeed or fail, failure modes), minor fixes by @tazlin in #112

New Contributors

• @dependabot made their first contribution in #98

Full Changelog: v2.1.1...v2.2.0

v2.1.1

Version 2.1.1

What's Changed

• feat: use latest comfyui (version as of Nov 10, 2023) by @tazlin in #92
• tests: updated expected images for lora+hires and k_dpmpp_sde by @tazlin in #94
• tests: fix more expected images by @tazlin in #95
• feat: use latest comfyui (as of Nov 10, 2023) by @tazlin in #93

Full Changelog: v2.1.0...v2.1.1

v2.1.0

Version 2.1.0

What's Changed

• docs: fix reference to old cuda version by @tazlin in #82
• feat: graceful fail if we detect a login redirect from civitai for loras by @tazlin in #89
• feat: use comfy dd116abfc48e8023bb425c2dd5bd954ee99d7a9c by @tazlin in #90
• v2.1.0 by @tazlin in #91

Full Changelog: v2.0.2...v2.1.0

v2.0.2

Version 2.0.2

What's Changed

• fix: better signal to comfyui lowvram mode is desired by @tazlin in #78
• feat: torch 2.1; better memory management in high vram scenarios by @tazlin in #80
• feat: use torch 2.1 + CU121 by @tazlin in #81

Full Changelog: v2.0.1...v2.0.2

v2.0.1

Version 2.0.1

What's Changed

• feat: add AIWORKER_LORA_CACHE_SIZE env var by @tazlin in #75
• fix: handle lora env var None by @tazlin in #77
• feat: patch in lora cache size env var support by @tazlin in #76

Full Changelog: v2.0.0...v2.0.1

v2.0.0

Version 2.0.0

What's Changed

• fix: use pre-commit for lint checks by @tazlin in #73
• refactor: hordelib now single threaded, no more need for .patch; feat: SDXL support by @tazlin in #68
• reGen by @tazlin in #74

Full Changelog: v1.6.6...v2.0.0

v1.6.6

Version 1.6.6

What's Changed

• fix: inject negative embeddings correctly by @tazlin in #70
• fix: inject negative embeddings correctly by @tazlin in #71

Full Changelog: v1.6.5...v1.6.6

v1.6.5

Version 1.6.5

What's Changed

• feat: Automatic downloading of TIs by @db0 in #55
• fix: TI now correctly compares to intended sha256 from hordeling by @tazlin in #65
• release: Support for TIs by @db0 in #66

Full Changelog: v1.6.4...v1.6.5