huggingface/diffusers

Pull Requests Commits

Release: v0.41.0-release

sayakpaul committed 6 days ago

086bf957

[tests] remove `test_pipelines_common.py` (#14669)

sayakpaul committed 6 days ago

Verified 77177984

[chore] remove force_upcast from autoencoder flux2 (#14946)

sayakpaul committed 6 days ago

Verified 899c9f3f

Configure fixed sampling sigmas on QwenImage21Pipeline (#14950)

naykun committed 7 days ago

Verified da1d3829

[tests] refactor the pipeline-level attention processor tests (#14701)

sayakpaul committed 7 days ago

Verified c2798cc7

[modular] Echo team joy future academy jd echo by @Gelercatty (#14941)

sayakpaul committed 7 days ago

Verified cff9dafb

Fix: Deprecating Siglip2ImageProcessorFast (#14781)

ariG23498 committed 7 days ago

Verified 9aababd7

agent docs: support only what released checkpoints use (#14750)

yiyixuxu committed 9 days ago

Verified 8b33bfc0

[Bugfix] Fix Cosmos3 FP8 tensor parallelism (#14921)

yzhautouskay committed 10 days ago

Verified 357f8738

Tag Krea 2 text encoder outputs as denoiser_input_fields (#14925)

tbsbngrtz committed 10 days ago

Verified 41566305

Add single file support for Krea 2 (#14914)

DN6 committed 11 days ago

Verified 578c9b2c

chore: add one additional copied from in qwenimage 2.1 vae (#14810)

sayakpaul committed 11 days ago

Verified 7997e4ea

Consolidate torch device backend dispatch (#14792)

DN6 committed 11 days ago

Verified acbabca3

Add single file support for Minimax H3 (#14839)

DN6 committed 11 days ago

Verified 4de185d6

[Modular] Avoid downloading weights when loading from an existing local path (#14797)

DN6 committed 11 days ago

Verified a91ff967

[core] Shard tensor-parallel checkpoints on load and save (#14544)

JingyaHuang committed 11 days ago

Verified 863092ff

[fix] Add return types (#14874)

stevhliu committed 12 days ago

Verified c60830ee

[Cosmos3] Fix Transfer SeaCache artifacts with control CFG (#14897)

yzhautouskay committed 12 days ago

Verified 78405ec9

Remove deprecated code paths (#14838)

DN6 committed 12 days ago

Verified a12c38a6

spit output to stderr when extracting GPU tests for PRs (#14847)

sayakpaul committed 12 days ago

Verified 031b2798

[docs] document release philosophy (#14904)

sayakpaul committed 12 days ago

Verified 56aa3cd6

[core] propagate sage attention updates. (#14584)

sayakpaul committed 13 days ago

Verified fef717ff

[diffusers-cli] add a dockerfile for diffusers cli hf jobs (#14550)

sayakpaul committed 13 days ago

Verified 4ac08e94

Fix LoRA loading for flattened CLIP text encoders (#14872)

BeyondBirthday07 committed 14 days ago

Verified 5ff8e59f

[LoRA] convert Z-Image LoRAs that only carry the fused qkv and bare out attention keys (#14875)

christopher5106 committed 14 days ago

Verified 8f0ad342

[realfill] Fix the LR scheduler when num_train_epochs is passed in a distributed training env (#14885)

825pranav committed 14 days ago

Verified 8315c5d6

[MInimax H3] Fix VAE decode (#14754)

asomoza committed 14 days ago

Verified 51a454be

downcast MiniMax-H3 position_ids at the device transfer on fp64-less backends (#14767)

SammyTourani committed 16 days ago

Verified e0abab83

Fix TaylorSeer cache crash when the feature shape changes between steps (#14831)

hide3tu committed 17 days ago

Verified bdc2bea3

[docs] Adapters (#14842)

stevhliu committed 18 days ago

Verified 4295ee3e

Older