huggingface/diffusers

Pull Requests Commits

[docs] Pipeline group offloading (#12286)

stevhliu committed 217 days ago

Verified 511056a4

sayakpaul committed 217 days ago

8e2d0383

Merge branch 'main' into support-group-offloading-pipeline-level

sayakpaul committed 217 days ago

Verified aa0cafbc

adjust criteria for marigold-intrinsics example on XPU (#12290)

kaixuanliu committed 218 days ago

Verified 4067d6c4

gguf new quant type support (with demo) (#12076)

calcuis committed 218 days ago

Verified 28106fca

DeepSpeed adaption for flux-kontext (#12240)

leisuzz committed 218 days ago

Verified c222570a

Support ControlNet-Inpainting for Qwen-Image (#12301)

haofanwang committed 218 days ago

Verified 4e36bb0d

[Modular] Qwen (#12220)

yiyixuxu committed 219 days ago

Verified f50b18ee

Merge branch 'main' into support-group-offloading-pipeline-level

sayakpaul committed 219 days ago

Verified 1a8ebf65

[docs] Models (#12248)

stevhliu committed 222 days ago

Verified fc337d58

[docs] Inference section cleanup (#12281)

stevhliu committed 222 days ago

Verified 32798bf2

Merge branch 'main' into support-group-offloading-pipeline-level

sayakpaul committed 222 days ago

Verified 506424c0

[docs] Sharing pipelines/models (#12280)

stevhliu committed 223 days ago

Verified c2e5ece0

sayakpaul committed 223 days ago

e141f5cf

feat: support group offloading at the pipeline level.

sayakpaul committed 223 days ago

25d9c70d

fix some typos (#12265)

co63oc committed 224 days ago

Verified 764b6247

Add AttentionMixin to WanVACETransformer3DModel (#12268)

J4BEZ committed 224 days ago

Verified 66829563

[tests] feat: add AoT compilation tests (#12203)

sayakpaul committed 224 days ago

Verified ffc8c0c1

[Quantization] Add TRT-ModelOpt as a Backend (#11173)

ishan-modi committed 224 days ago

Verified 4acbfbf1

[docs] AutoPipeline (#12160)

stevhliu committed 224 days ago

Verified 6549b04e

[core] use `kernels` to support `_flash_3_hub` attention backend (#12236)

sayakpaul committed 224 days ago

Verified 130fd8df

[CI] Remove big accelerator requirements from Quanto Tests (#12266)

DN6 committed 224 days ago

Verified bcd4d77b

[Flux LoRA] fix for prior preservation and mixed precision sampling, follow up on #11873 (#12264)

linoytsaban committed 225 days ago

Verified 006d0927

[docs] Fix VAE scale factor calculation in distributed inference docs (#12259)

Men1scus committed 225 days ago

Verified 9e4a75b1

[fix] fix for prior preservation and mixed precision sampling (#11873)

Brvcket committed 226 days ago

Verified 0ff1aa91

Fix lora conversion function for ai-toolkit Qwen Image LoRAs (#12261)

apolinario committed 226 days ago

Verified 901da9dc

Add Qwen-Image-Edit Inpainting pipeline (#12225)

Trgtuan10 committed 227 days ago

Verified 67ffa703

Improve performance of NPU FA (#12260)

leisuzz committed 228 days ago

Verified 827fad66

[QwenImageEditPipeline] Add image entry in __call__ function (#12254)

Trgtuan10 committed 228 days ago

Verified 9b721db2

[Modular] Consolidate `load_default_components` into `load_components` (#12217)

DN6 committed 230 days ago

Verified ba0e732e

Older