huggingface/diffusers

Pull Requests Commits

Merge branch 'main' into version-checks-cache

cbensimon committed 35 days ago

Verified 6c12a205

make flux ready for mellon (#12419)

sayakpaul committed 35 days ago

Verified 7f3e9b86

[FIX] Text to image training peft version (#12434)

SahilCarterr committed 36 days ago

Verified ce90f9b2

[core] support QwenImage Edit Plus in modular (#12416)

sayakpaul committed 36 days ago

Verified c3675d4c

fix scale_shift_factor being on cpu for wan and ltx (#12347)

vladmandic committed 37 days ago

Verified 2b7deffe

[training-scripts] Make more examples UV-compatible (follow up on #12000) (#12407)

linoytsaban committed 38 days ago

Verified 941ac9c3

FIX Test to ignore warning for enable_lora_hotswap (#12421)

BenjaminBossan committed 39 days ago

Verified 7242b5ff

[core] conditionally import torch distributed stuff. (#12420)

sayakpaul committed 39 days ago

Verified b4297967

[ci] xfail failing tests in CI. (#12418)

sayakpaul committed 39 days ago

Verified 9ae5b629

[tests] cache non lora pipeline outputs. (#12298)

sayakpaul committed 41 days ago

Verified 814d710e

[docs] Migrate syntax (#12390)

stevhliu committed 41 days ago

Verified cc5b31ff

[docs] CP (#12331)

stevhliu committed 41 days ago

Verified d7a1a036

Install latest prerelease from huggingface_hub when installing transformers from main (#12395)

Wauplin committed 41 days ago

Verified b5965454

fix 3 xpu failures uts w/ latest pytorch (#12408)

yao-matrix committed 41 days ago

Verified 0e12ba74

[Tests] Add single file tester mixin for Models and remove unittest dependency (#12352)

DN6 committed 41 days ago

Verified 20fd00b1

[modular]some small fix (#12307)

yiyixuxu committed 42 days ago

Verified 76d4e416

[docs] Model formats (#12256)

stevhliu committed 42 days ago

Verified c07fcf78

[docs] Distributed inference (#12285)

stevhliu committed 42 days ago

Verified ccedeca9

[quantization] feat: support aobaseconfig classes in `TorchAOConfig` (#12275)

sayakpaul committed 42 days ago

Verified 64a5187d

Fix #12116: preserve boolean dtype for attention masks in ChromaPipeline (#12263)

akshay-babbar committed 42 days ago

Verified 0a151115

Don't skip Qwen model tests for group offloading with disk (#12382)

sayakpaul committed 42 days ago

Verified 19085ac8

[docs] remove docstrings from repeated methods in `lora_pipeline.py` (#12393)

sayakpaul committed 45 days ago

Verified 041501ae

[docs] slight edits to the attention backends docs. (#12394)

sayakpaul committed 45 days ago

Verified 9c094458

lru_cache for Python 3.8

cbensimon committed 45 days ago

Verified 39216fc9

[perf] Cache version checks

cbensimon committed 45 days ago

Verified 2ca3cadb

[CI] disable installing transformers from main in ci for now. (#12397)

sayakpaul committed 45 days ago

Verified 4588bbeb

Support both huggingface_hub `v0.x` and `v1.x` (#12389)

Wauplin committed 46 days ago

Verified ec5449f3

Introduce cache-dit to community optimization (#12366)

DefTruth committed 47 days ago

Verified 310fdaf5

Context Parallel w/ Ring & Ulysses & Unified Attention (#11941)

a-r-r-o-w committed 47 days ago

Verified dcb6dd9b

Fix WanVACEPipeline to allow prompt to be None and skip encoding step (#12251)

albchim committed 47 days ago

Verified 043ab252

Older