分支列表

默认分支

main
frontend tests / frontend-tests (push) Has been cancelled
python checks / python-checks (push) Has been cancelled
lfs checks / lfs-check (push) Has been cancelled
openapi checks / openapi-checks (push) Has been cancelled
python tests / py3.11: macos-default (push) Has been cancelled
python tests / py3.12: macos-default (push) Has been cancelled
python tests / py3.11: windows-cpu (push) Has been cancelled
python tests / py3.12: windows-cpu (push) Has been cancelled
python tests / py3.11: linux-cpu (push) Has been cancelled
build container image / cpu (push) Has been cancelled
build container image / cuda (push) Has been cancelled
build container image / rocm (push) Has been cancelled
docs / changes (push) Has been cancelled
frontend checks / frontend-checks (push) Has been cancelled
python tests / py3.12: linux-cpu (push) Has been cancelled
typegen checks / typegen-checks (push) Has been cancelled
uv lock checks / uv-lock-checks (push) Has been cancelled
docs / check-and-build (push) Has been cancelled
docs / deploy (push) Has been cancelled

8486d47b7f · ci: keep pins.json in sync with pyproject.toml (#9351) · 最后更新于 2026-08-05 16:36:40 +00:00

分支列表

f01e41ceaf · First pass at dynamically calculating the working memory requirements for the VAE decoding operation. Still need to tune SD3 and FLUX. · 最后更新于 2024-12-19 20:26:16 +00:00    frostbyte_neo

3989
57

3ed6e65a6e · Enable LoRAPatcher.apply_smart_lora_patches(...) throughout the stack. · 最后更新于 2024-12-12 22:41:50 +00:00    frostbyte_neo

4051
15

5422bb74c6 · ruff · 最后更新于 2024-12-12 22:28:44 +00:00    frostbyte_neo

4051
5

f109914eb3 · WIP - messing around with some alternative autocast implementations · 最后更新于 2024-12-11 02:58:56 +00:00    frostbyte_neo

4075
38

a1a3e60431 · feat(app): process accepts custom invocation context builder · 最后更新于 2024-12-10 22:54:02 +00:00    frostbyte_neo

4051
1

f6045682c0 · Fix bug with partial offload of model buffers. · 最后更新于 2024-12-10 22:19:17 +00:00    frostbyte_neo

4075
37

2144d21f80 · Maintain a read-only CPU state dict copy in CachedModelWithPartialLoad. · 最后更新于 2024-12-06 21:49:24 +00:00    frostbyte_neo

4075
23

987393853c · Create CachedModelOnlyFullLoad class. · 最后更新于 2024-12-05 18:43:50 +00:00    frostbyte_neo

4075
16

a81acacb2a · fix ruff error · 最后更新于 2024-12-03 00:37:51 +00:00    frostbyte_neo

4068
19

8d04ec3f95 · Improve docs related to dynamic T5 sequence length selection. · 最后更新于 2024-11-29 16:11:51 +00:00    frostbyte_neo

4101
2

437d1087a2 · Dynamically select smaller t5 seq len to save inference time. · 最后更新于 2024-11-29 00:15:32 +00:00    frostbyte_neo

4131
4

e22f0f2203 · Update DepthAnything post-processing logic to avoid artifacts caused by numerical overflow. · 最后更新于 2024-11-27 14:54:30 +00:00    frostbyte_neo

4133
1

182c5793ba · Commented pytorch profiler. · 最后更新于 2024-11-24 04:58:01 +00:00    frostbyte_neo

4140
4

711f47280c · Add test state dict shape for FLUX kohya LoRA models with both te1 and te3 layers. · 最后更新于 2024-11-21 22:48:23 +00:00    frostbyte_neo

4141
1

4ffe831958 · Add ConcatenateImagesInvocation. · 最后更新于 2024-11-19 20:07:50 +00:00    frostbyte_neo

4187
1

ceae1dc04f · chore: bump version to v5.4.1 · 最后更新于 2024-11-15 00:21:24 +00:00    frostbyte_neo

4243
1

0fb3b53446 · Add test state dict for a FLUX DoRA model. · 最后更新于 2024-11-14 19:13:40 +00:00    frostbyte_neo

4250
1

c3304dcbe3 · feat(ui): add image batching to workflows (wip) · 最后更新于 2024-11-13 22:23:04 +00:00    frostbyte_neo

4299
1

22c53dce45 · Add unit tests for FLUX diffusers LoRA without .proj_mlp layers. · 最后更新于 2024-11-13 22:17:59 +00:00    frostbyte_neo

4302
3

922f8e3749 · wip · 最后更新于 2024-11-08 20:32:45 +00:00    frostbyte_neo

4302
1