pypi-diffusers: Autospec creation for update from version 0.30.3 to version 0.31.0

0x名無し (1):
      Dreambooth lora flux bug 3dtensor to 2dtensor (#9653)

Ahnjj_DEV (1):
      Fix some documentation in ./src/diffusers/models/adapter.py (#9591)

Anand Kumar (2):
      [train_custom_diffusion.py] Fix the LR schedulers when `num_train_epochs` is passed in a distributed training env (#9308)
      [train_instruct_pix2pix.py]Fix the LR schedulers when `num_train_epochs` is passed in a distributed training env (#9316)

Anatoly Belikov (1):
      adapt masked im2im pipeline for SDXL (#7790)

Aryan (24):
      [refactor] CogVideoX followups + tiled decoding support (#9150)
      [tests] fix broken xformers tests (#9206)
      AnimateDiff prompt travel (#9231)
      [docs] Add a note on torchao/quanto benchmarks for CogVideoX and memory-efficient inference (#9296)
      [core] CogVideoX memory optimizations in VAE encode (#9340)
      [core] Support VideoToVideo with CogVideoX (#9333)
      [tests] remove/speedup some low signal tests (#9285)
      [refactor] move positional embeddings to patch embed layer for CogVideoX (#9263)
      [core] Freenoise memory improvements (#9262)
      [docs] AnimateDiff FreeNoise  (#9414)
      Allow max shard size to be specified when saving pipeline (#9440)
      Remove CogVideoX mentions from single file docs; Test updates (#9444)
      set max_shard_size to None for pipeline save_pretrained (#9447)
      [training] CogVideoX Lora (#9302)
      [refactor] LoRA tests (#9481)
      [bug] Precedence of operations in VAE should be slicing -> tiling (#9342)
      [refactor] remove conv_cache from CogVideoX VAE (#9524)
      [training] CogVideoX-I2V LoRA (#9482)
      [pipeline] CogVideoX-Fun Control (#9671)
      [core] improve VAE encode/decode framewise batching (#9684)
      [tests] fix name and unskip CogI2V integration test (#9683)
      [refactor] DiffusionPipeline.download (#9557)
      [CI] pin max torch version to fix CI errors (#9709)
      `make  deps_table_update` to fix CI tests (#9720)

Beinsezii (1):
      Add Lumina T2I Auto Pipe Mapping (#8962)

Benjamin Bossan (1):
      MAINT Permission for GH token in stale.yml (#9427)

C (1):
      [Flux] Optimize guidance creation in flux pipeline by moving it outside the loop (#9153)

Charchit Sharma (2):
      refactor image_processor.py file (#9608)
      Resolves [BUG] 'GatheredParameters' object is not callable (#9614)

Chenyu Li (1):
      Fix typo in cogvideo pipeline (#9722)

Clem (1):
      fix xlabs FLUX lora conversion typo (#9581)

Daniel Socek (1):
      Fix textual inversion SDXL and add support for 2nd text encoder (#9010)

Darren Hsu (1):
      Support bfloat16 for Upsample2D (#9480)

David Steinberg (1):
      Fix a dead link (#9116)

Dhruv Nair (22):
      Update Video Loading/Export to use `imageio` (#9094)
      Small improvements for video loading (#9183)
      Update `is_safetensors_compatible` check (#8991)
      [CI] Multiple Slow Test fixes.  (#9198)
      [CI] Add `fail-fast=False` to CUDA nightly and slow tests (#9214)
      Remove M1 runner from Nightly Test (#9193)
      [Single File] Fix configuring scheduler via legacy kwargs (#9229)
      [Single File] Support loading Comfy UI Flux checkpoints (#9243)
      [Single File] Add Flux Pipeline Support  (#9244)
      [CI] Run Fast + Fast GPU Tests on release branches.  (#9255)
      Fix Freenoise for AnimateDiff V3 checkpoint.   (#9288)
      [CI] Update Release Tests (#9274)
      Fix Flux CLIP prompt embeds repeat for num_images_per_prompt > 1 (#9280)
      [CI] Update Hub Token on nightly tests (#9318)
      [CI] More fixes for Fast GPU Tests on main (#9300)
      [CI] More Fast GPU Test Fixes  (#9346)
      [CI] Add option to dispatch Fast GPU tests on main  (#9355)
      [CI] Update Single file Nightly Tests (#9357)
      [CI] Quick fix for Cog Video Test (#9373)
      [CI] Nightly Test Updates (#9380)
      Fix typos (#9739)
      is_safetensors_compatible fix (#9741)

Dibbla! (1):
      Errata - fix typo (#9100)

Disty0 (1):
      Custom sampler support for Stable Cascade Decoder (#9132)

Eduardo Escobar (1):
      Enable `load_lora_weights` for `StableDiffusion3InpaintPipeline` (#9330)

Elias Rad (1):
      Docs fix spelling issues (#9219)

Eliseu Silva (1):
      Fix for use_safetensors parameters, allow use of parameter on loading submodels (#9576) (#9587)

Fanli Lin (1):
      [tests] make 2 tests device-agnostic   (#9347)

Frank (Haofan) Wang (1):
      Update __init__.py (#9286)

G.O.D (1):
      [bugfix] reduce float value error when adding noise (#9004)

GSSun (1):
      fix IsADirectoryError when running the training code for sd3_dreambooth_lora_16gb.ipynb (#9634)

Haruya Ishikawa (1):
      fix one uncaught deprecation warning for accessing vae_latent_channels in VaeImagePreprocessor (#9372)

Igor Filippov (1):
      [Pipeline] animatediff + vid2vid + controlnet (#9337)

Jianqi Pan (1):
      fix(pipeline): k sampler sigmas device (#9189)

Jinzhe Pan (2):
      [docs] Add xDiT in section optimization  (#9365)
      [docs] Fix xDiT doc image damage (#9655)

Jiwook Han (2):
      Reflect few contributions on `contribution.md` that were not reflected on #8294 (#8938)
      [doc] Fix some docstrings in `src/diffusers/training_utils.py` (#9606)

Jongho Choi (1):
      [peft] simple update when unscale  (#9689)

Juan Acevedo (1):
      Ptxla sd training (#9381)

JuanCarlosPi (1):
      Add PAG support to StableDiffusionControlNetPAGInpaintPipeline  (#8875)

Lee Penkman (1):
      Update community_projects.md (#9266)

Leo Jiang (3):
      Fix dtype error for StableDiffusionXL (#9217)
      Fix the issue on sd3 dreambooth w./w.t. lora training (#9419)
      Improve the performance and suitable for NPU computing (#9642)

Linoy Tsaban (9):
      [Flux] Dreambooth LoRA training scripts (#9086)
      [Flux Dreambooth LoRA] - te bug fixes & updates (#9139)
      [Dreambooth flux] bug fix for dreambooth script (align with dreambooth lora) (#9257)
      improve README for flux dreambooth lora (#9290)
      [Flux Dreambooth lora] add latent caching (#9160)
      [Flux with CFG] add flux pipeline with cfg support  (#9445)
      [SD3 dreambooth-lora training] small updates + bug fixes  (#9682)
      [Flux] Add advanced training script + support textual inversion inference (#9434)
      [advanced flux lora script] minor updates to readme (#9705)

LukeLin (1):
      [Doc] Fix path and and also import imageio (#9506)

M Saqlain (3):
      [Tests] Improve transformers model test suite coverage - Lumina (#8987)
      [Tests] Reduce the model size in the lumina test  (#8985)
      Add Differential Diffusion to Kolors (#9423)

Marçal Comajoan Cara (1):
      Replace transformers.deepspeed with transformers.integrations.deepspeed (#9281)

Monjoy Narayan Choudhury (1):
      Add Differential Diffusion to HunyuanDiT. (#9040)

Pakkapon Phongthawee (1):
      make controlnet support interrupt (#9620)

PromeAI (1):
      [examples] add train flux-controlnet scripts in example. (#9324)

Robin (1):
      [Fix] when run load pretain with local_files_only, local variable 'cached_folder' referenced before assignment (#9376)

Ryan Lin (1):
      Flux - soft inpainting via differential diffusion (#9268)

SahilCarterr (2):
      add PAG support for SD Img2Img (#9463)
      Added Lora Support to SD3 Img2Img Pipeline (#9659)

Sangwon Lee (1):
      Fix StableDiffusionXLPAGInpaintPipeline (#9128)

Sayak Paul (39):
      Update README.md to include InstantID (#8770)
      Update distributed_inference.md to include a fuller example on distributed inference (#9152)
      feat: allow flux transformer to be sharded during inference  (#9159)
      [Chore] add set_default_attn_processor to pixart. (#9196)
      feat: allow sharding for auraflow. (#8853)
      [Core] Tear apart `from_pretrained()` of `DiffusionPipeline` (#8967)
      [Flux LoRA] support parsing alpha from a flux lora state dict. (#9236)
      [Core] fuse_qkv_projection() to Flux (#9185)
      [LoRA] support kohya and xlabs loras for flux. (#9295)
      chore: add a cleaning utility to be useful during training. (#9240)
      modify benchmarks to replace sdv1.5 with dreamshaper. (#9334)
      [Tests] fix some fast gpu tests. (#9379)
      [CI] update artifact uploader version (#9426)
      [LoRA] fix adapter movement when using DoRA. (#9411)
      [CI] make runner_type restricted. (#9441)
      [CI] updates to the CI report naming, and `accelerate` installation (#9429)
      [Flux] add lora integration tests. (#9353)
      [CI] fix nightly model tests (#9483)
      [Cog] some minor fixes and nits (#9466)
      [CI] allow faster downloads from the Hub in CI. (#9478)
      [Community Pipeline] Batched implementation of Flux with CFG (#9513)
      [LoRA] make set_adapters() method more robust. (#9535)
      [Tests] [LoRA] clean up the serialization stuff. (#9512)
      [Core] fix variant-identification. (#9253)
      [chore] fix: retain memory utility. (#9543)
      [LoRA] support Kohya Flux LoRAs that have text encoders as well (#9542)
      [Chore] add a note on the versions in Flux LoRA integration tests (#9598)
      Update distributed_inference.md to include `transformer.device_map` (#9553)
      [LoRA] Handle DoRA better (#9547)
      [LoRA] allow loras to be loaded with low_cpu_mem_usage. (#9510)
      [LoRA] fix dora test to catch the warning properly. (#9627)
      [CI] replace ubuntu version to 22.04. (#9656)
      [Tests] increase transformers version in `test_low_cpu_mem_usage_with_loading` (#9662)
      [Chore] fix import of EntryNotFoundError. (#9676)
      [LoRA] log a warning when there are missing keys in the LoRA loading. (#9622)
      [Docker] pin torch versions in the dockerfiles. (#9721)
      [Quantization] Add quantization support for `bitsandbytes` (#9213)
      [Docs] docs to xlabs controlnets. (#9688)
      [bitsandbbytes] follow-ups (#9730)

Seongbin Lim (1):
      Allow DDPMPipeline half precision (#9222)

Simo Ryu (1):
      Add Learned PE selection for Auraflow (#9182)

Steven Liu (5):
      [docs] Organize model toctree (#9118)
      [docs] Resolve internal links to PEFT (#9144)
      [docs] Network alpha docstring (#9238)
      [docs] Add pipelines to table (#9282)
      [docs] Model sharding (#9521)

Subho Ghosh (2):
      Feature flux controlnet img2img and inpaint pipeline (#9408)
      flux controlnet control_guidance_start and control_guidance_end implement (#9571)

Tolga Cangöz (4):
      [`Docs`] Fix CPU offloading usage (#9207)
      Update `UNet2DConditionModel`'s error messages (#9230)
      [`Community Pipeline`] Add 🪆Matryoshka Diffusion Models (#9157)
      Fix `schedule_shifted_power` usage in 🪆Matryoshka Diffusion Models (#9723)

Vinh H. Pham (1):
      StableDiffusionLatentUpscalePipeline - positive/negative prompt embeds support (#8947)

Vishnu V Jaddipal (3):
      Fix ```from_single_file``` for xl_inpaint (#9054)
      Xlabs lora fix (#9348)
      Add Flux inpainting and Flux Img2Img (#9135)

Vladimir Mandic (1):
      Several fixes to Flux ControlNet pipelines (#9472)

Wenlong Wu (1):
      Add loading text inversion (#9130)

Xiangchendong (1):
      fix cogvideox autoencoder decode (#9569)

YiYi Xu (18):
      fix autopipeline for kolors img2img (#9212)
      fix a regression in `is_safetensors_compatible` (#9234)
      Flux followup (#9074)
      fix _identify_model_variants (#9247)
      refactor 3d rope for cogvideox  (#9269)
      rotary embedding refactor 2: update comments, fix dtype for use_real=False (#9312)
      refactor rotary embedding 3: so it is not on cpu (#9307)
      update runway repo for single_file (#9323)
      small update on rotary embedding (#9354)
      add flux inpaint + img2img + controlnet to auto pipeline (#9367)
      refactor `get_timesteps` for SDXL img2img + add set_begin_index (#9375)
      a few fix for SingleFile tests (#9522)
      update get_parameter_dtype (#9526)
      flux controlnet fix (control_modes batch & others) (#9507)
      [sd3] make sure height and size are divisible by `16` (#9573)
      [authored by @Anghellia) Add support of Xlabs Controlnets #9638 (#9687)
      minor doc/test update (#9734)
      fix singlestep dpm tests (#9716)

Yijun Lee (2):
      refac: docstrings in import_utils.py (#9583)
      refac/pipeline_output (#9582)

Yu Zheng (2):
      [examples] add controlnet sd3 example (#9249)
      Update sd3 controlnet example (#9735)

Yuxuan.Zhang (2):
      CogVideoX-5b-I2V support (#9418)
      CogView3Plus DiT (#9570)

Zoltan (1):
      Add vae slicing and tiling to flux pipeline (#9122)

apolinário (1):
      Change default for `guidance_scale`in FLUX (#9305)

asfiyab-nvidia (1):
      FluxPosEmbed: Remove Squeeze No-op (#9409)

bonlime (1):
      Fix bug in Textual Inversion Unloading (#9304)

captainzz (3):
      fix from_transformer() with extra conditioning channels (#9364)
      fix bugs for sd3 controlnet training (#9489)
      fix vae dtype when accelerate config using --mixed_precision="fp16" (#9601)

dependabot[bot] (2):
      Bump torch from 2.0.1 to 2.2.0 in /examples/research_projects/realfill (#8971)
      Bump jinja2 from 3.1.3 to 3.1.4 in /examples/research_projects/realfill (#7873)

dianyo (1):
      Migrate the BrownianTree to BrownianInterval in DPM solver (#9335)

glide-the (2):
      fix: CogVideox train dataset _preprocess_data crop video (#9574)
      Docs: CogVideoX (#9578)

hlky (12):
      [Schedulers] Add exponential sigmas / exponential noise schedule (#9499)
      Add Noise Schedule/Schedule Type to Schedulers Overview documentation (#9504)
      Add exponential sigmas to other schedulers and update docs (#9518)
      [Schedulers] Add beta sigmas / beta noise schedule (#9509)
      Add beta sigmas to other schedulers and update docs (#9538)
      FluxMultiControlNetModel (#9647)
      Add pred_original_sample to `if not return_dict` path (#9649)
      Convert list/tuple of `SD3ControlNetModel` to `SD3MultiControlNetModel` (#9652)
      Convert list/tuple of `HunyuanDiT2DControlNetModel` to `HunyuanDiT2DMultiControlNetModel` (#9651)
      Refactor SchedulerOutput and add pred_original_sample in `DPMSolverSDE`, `Heun`, `KDPM2Ancestral` and `KDPM2` (#9650)
      Slight performance improvement to `Euler`, `EDMEuler`, `FlowMatchHeun`, `KDPM2Ancestral` (#9616)
      Add prompt scheduling callback to community scripts (#9718)

pibbo88 (1):
      Fix the bug of sd3 controlnet training when using gradient checkpointing. (#9498)

sanaka (1):
      Fix the bug that `joint_attention_kwargs` is not passed to the FLUX's transformer attention processors (#9517)

satani99 (1):
      Add StableDiffusionXLControlNetPAGImg2ImgPipeline (#8990)

sayakpaul (1):
      Release: v0.31.0

sayantan sadhu (1):
      fix for lr scheduler in distributed training (#9103)

suzukimain (1):
      [docs] Replace runwayml/stable-diffusion-v1-5 with Lykon/dreamshaper-8 (#9428)

timdalxx (1):
      [docs] add docstrings in `pipline_stable_diffusion.py` (#9590)

townwish4git (1):
      fix(sd3): fix deletion of text_encoders etc (#8951)

v2ray (2):
      [Doc] Improved level of clarity for latents_to_rgb. (#9529)
      Fixed noise_pred_text referenced before assignment. (#9537)

wony617 (2):
      [docs] refactoring docstrings in `community/hd_painter.py` (#9593)
      [docs] refactoring docstrings in `models/embeddings_flax.py` (#9592)

yangpei-comp (1):
      Bugfix in `pipeline_kandinsky2_2_combined.py`: Image type check mismatch (#9256)

zR (1):
      Cogvideox-5B Model adapter change (#9203)

Álvaro Somoza (5):
      post release 0.30.0 (#9173)
      [IP Adapter] Fix object has no attribute with image encoder (#9194)
      [IP Adapter] Fix `cache_dir` and `local_files_only` for image encoder (#9272)
      [Tests] Fix ChatGLMTokenizer (#9536)
      [Fix] Using sharded checkpoints with gated repositories (#9737)

林金鹏 (1):
      Support SD3 controlnet inpainting (#9099)

王奇勋 (2):
      [FLUX] Support ControlNet (#9126)
      [Flux] Support Union ControlNet (#9175)

Author: fenrus75

Makefile

@@ -1,5 +1,5 @@
 PKG_NAME := pypi-diffusers
-URL = https://files.pythonhosted.org/packages/de/a9/a53a3d0c0a277a5002aa1e625d0e651b2957f901438052d8d47a97703883/diffusers-0.30.3.tar.gz
+URL = https://files.pythonhosted.org/packages/78/5d/156acb741303abbee214926804c5f0d09eacd35d05ad942577e996acdac3/diffusers-0.31.0.tar.gz
 ARCHIVES = 
 
 include ../common/Makefile.common

options.conf

@@ -1,6 +1,6 @@
 [package]
 name = pypi-diffusers
-url = https://files.pythonhosted.org/packages/de/a9/a53a3d0c0a277a5002aa1e625d0e651b2957f901438052d8d47a97703883/diffusers-0.30.3.tar.gz
+url = https://files.pythonhosted.org/packages/78/5d/156acb741303abbee214926804c5f0d09eacd35d05ad942577e996acdac3/diffusers-0.31.0.tar.gz
 archives = 
 giturl = https://github.com/huggingface/diffusers/
 domain = 

pypi-diffusers.spec

@@ -2,14 +2,14 @@
 # This file is auto-generated. DO NOT EDIT
 # Generated by: autospec.py
 # Using build pattern: pyproject
-# autospec version: v19
+# autospec version: v20
 # autospec commit: f35655a
 #
 Name     : pypi-diffusers
-Version  : 0.30.3
-Release  : 58
-URL      : https://files.pythonhosted.org/packages/de/a9/a53a3d0c0a277a5002aa1e625d0e651b2957f901438052d8d47a97703883/diffusers-0.30.3.tar.gz
-Source0  : https://files.pythonhosted.org/packages/de/a9/a53a3d0c0a277a5002aa1e625d0e651b2957f901438052d8d47a97703883/diffusers-0.30.3.tar.gz
+Version  : 0.31.0
+Release  : 59
+URL      : https://files.pythonhosted.org/packages/78/5d/156acb741303abbee214926804c5f0d09eacd35d05ad942577e996acdac3/diffusers-0.31.0.tar.gz
+Source0  : https://files.pythonhosted.org/packages/78/5d/156acb741303abbee214926804c5f0d09eacd35d05ad942577e996acdac3/diffusers-0.31.0.tar.gz
 Summary  : State-of-the-art diffusion in PyTorch and JAX.
 Group    : Development/Tools
 License  : Apache-2.0
@@ -73,18 +73,18 @@ python3 components for the pypi-diffusers package.
 
 
 %prep
-%setup -q -n diffusers-0.30.3
-cd %{_builddir}/diffusers-0.30.3
+%setup -q -n diffusers-0.31.0
+cd %{_builddir}/diffusers-0.31.0
 pushd ..
-cp -a diffusers-0.30.3 buildavx2
+cp -a diffusers-0.31.0 buildavx2
 popd
 
 %build
 export http_proxy=http://127.0.0.1:9/
 export https_proxy=http://127.0.0.1:9/
 export no_proxy=localhost,127.0.0.1,0.0.0.0
 export LANG=C.UTF-8
-export SOURCE_DATE_EPOCH=1726581482
+export SOURCE_DATE_EPOCH=1729626155
 export GCC_IGNORE_WERROR=1
 export AR=gcc-ar
 export RANLIB=gcc-ranlib

release

@@ -1 +1 @@
-58
+59

upstream

@@ -1 +1 @@
-4eb4eabc73b263ba9be844cf9f3045cfcdbbad56/diffusers-0.30.3.tar.gz
+7c719172b1b72c1ff079900e6f4f403da8e1bd90/diffusers-0.31.0.tar.gz