Pull Requests huggingface/diffusers

adjust unit tests for `test_save_load_float16`

#12500 opened 2025-10-17 02:14 by kaixuanliu

GGUF fix for unquantized types when using unquantize kernels

#12498 opened 2025-10-16 18:09 by dxqb

purge HF_HUB_ENABLE_HF_TRANSFER; promote Xet

#12497 opened 2025-10-16 12:38 by Vaibhavs10

Fix wan i2v condition shape mismatch

#12496 opened 2025-10-16 10:56 by DefTruth

replace FeatureExtractor to ImageProcessor

#12495 opened 2025-10-16 03:10 by jiqing-feng

fix constants.py to user `upper()`

#12479 opened 2025-10-14 08:57 by sayakpaul

Kandinsky 5 is finally in Diffusers!

#12478 opened 2025-10-13 22:43 by leffff

[Feature] Add support for Lumina-T2I in diffusers

#12476 opened 2025-10-13 11:16 by Bili-Sakura

[core] Refactor hub attn kernels

#12475 opened 2025-10-13 10:14 by sayakpaul

fix CI bug for kandinsky3_img2img case

#12474 opened 2025-10-13 06:22 by kaixuanliu

[core] `AutoencoderMixin` to abstract common methods great-unbloating

#12473 opened 2025-10-13 04:53 by sayakpaul

Add update expected / unexpected keys api to DiffusersQuantizer

#12471 opened 2025-10-11 14:58 by Disty0

Support for lumina dimoo

#12468 opened 2025-10-11 04:17 by qianyu-dlut

[FIX] Fixes QwenImagePipeline batch issue

#12467 opened 2025-10-10 23:23 by SahilCarterr

[core] reuse `AttentionMixin` for compatible classes great-unbloating

#12463 opened 2025-10-10 15:32 by sayakpaul

Loose the criteria tolerance appropriately for Intel XPU devices

#12460 opened 2025-10-10 06:03 by kaixuanliu

Add Photon model and pipeline support

#12456 opened 2025-10-09 13:21 by DavidBert

Fix `QwenImageEditPlusPipeline` not using the passed in width/height for the VAE

#12453 opened 2025-10-09 08:24 by cakedan

Remove Qwen Image Redundant RoPE Cache

#12452 opened 2025-10-09 01:12 by dg845

Fix MPS compatibility in get_1d_sincos_pos_embed_from_grid #12432

#12449 opened 2025-10-07 19:21 by Aishwarya0811

Fix checkpoint overwrite bug in train_sana_sprint_diffusers

#12448 opened 2025-10-07 17:19 by Aishwarya0811

Fix Context Parallel validation checks

#12446 opened 2025-10-07 12:22 by DN6

Fix Flux Context Parallel Bug (Incoherent Image Generation)

#12443 opened 2025-10-06 23:54 by mali-afridi

Add Wan2.2-Animate: Unified Character Animation and Replacement with Holistic Replication

#12442 opened 2025-10-06 18:56 by tolgacangoz

[core] support sage attention through `kernels` performance

#12439 opened 2025-10-06 05:48 by sayakpaul

[Pipelines] Enable Wan VACE to run since single transformer

#12428 opened 2025-10-03 11:21 by DN6

Migrate lora pipeline tests to use `pytest`

#12426 opened 2025-10-03 07:25 by sayakpaul

add bucket for sdxl lora and dreambooth script traing

#12413 opened 2025-10-01 06:38 by Light-yzc

Fix prior preservation encoding in DreamBooth SD3(&its LoRA version) training scripts

#12411 opened 2025-09-30 14:54 by Barque-S

Fix prompt isolation tests for QwenImage edit and edit plus

#12403 opened 2025-09-28 10:52 by sayakpaul