You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository was archived by the owner on Aug 11, 2025. It is now read-only.
pypi-diffusers: Autospec creation for update from version 0.31.0 to version 0.32.0
Abhipsha Das (1):
[Model Card] standardize advanced diffusion training sd15 lora (#7613)
Aditya Raj (1):
[BUG FIX] [Stable Audio Pipeline] Resolve torch.Tensor.new_zeros() TypeError in function prepare_latents caused by audio_vae_length (#10306)
Anand Kumar (1):
[Bug fix] "previous_timestep()" in DDPM scheduling compatible with "trailing" and "linspace" options (#9384)
Andrés Romero (1):
Flux Control(Depth/Canny) + Inpaint (#10192)
Aritra Roy Gosthipaty (1):
[Guide] Quantize your Diffusion Models with `bnb` (#10012)
Aryan (32):
[core] Allegro T2V (#9736)
Allegro VAE fix (#9811)
[core] Mochi T2V (#9769)
Make CogVideoX RoPE implementation consistent (#9963)
Fix prepare latent image ids and vae sample generators for flux (#9981)
Flux Fill, Canny, Depth, Redux (#9985)
[docs] Fix CogVideoX table (#10008)
Use torch.device instead of current device index for BnB quantizer (#10069)
Remove duplicate checks for len(generator) != batch_size when generator is a list (#10134)
[Single file] Support `revision` argument when loading single file config (#10168)
Flux Control LoRA (#9999)
[core] LTX Video (#10021)
Test error raised when loading normal and expanding loras together in Flux (#10188)
[core] Hunyuan Video (#10136)
[core] TorchAO Quantizer (#10009)
Fix copied from comment in Mochi lora loader (#10255)
[LoRA] Support LTX Video (#10228)
[docs] Clarify dtypes for Sana (#10248)
[tests] Remove/rename unsupported quantization torchao type (#10263)
[tests] Fix broken cuda, nightly and lora tests on main for CogVideoX (#10270)
Rename Mochi integration test correctly (#10220)
[tests] remove nullop import checks from lora tests (#10273)
Hunyuan VAE tiling fixes and transformer docs (#10295)
Fix failing lora tests after HunyuanVideo lora (#10307)
Add support for sharded models when TorchAO quantization is enabled (#10256)
Make tensors in ResNet contiguous for Hunyuan VAE (#10309)
Community hosted weights for diffusers format HunyuanVideo weights (#10344)
Bump minimum TorchAO version to 0.7.0 (#10293)
[tests] Refactor TorchAO serialization fast tests (#10271)
Fix failing CogVideoX LoRA fuse test (#10352)
Rename LTX blocks and docs title (#10213)
[core] LTX Video 0.9.1 (#10330)
Bagheera (1):
add skip_layers argument to SD3 transformer model class (#9880)
Benjamin Paine (2):
Fix Progress Bar Updates in SD 1.5 PAG Img2Img pipeline (#9925)
Add StableDiffusion3PAGImg2Img Pipeline + Fix SD3 Unconditional PAG (#9932)
Bios (1):
update StableDiffusion3Img2ImgPipeline.add image size validation (#10166)
Biswaroop (1):
[Fix] remove setting lr for T5 text encoder when using prodigy in flux dreambooth lora script (#9473)
Boseong Jeon (1):
Handling mixed precision for dreambooth flux lora training (#9565)
Canva (1):
Add support for XFormers in SD3 (#8583)
ChG (1):
fix link in the docs (#10058)
DTG (1):
Fix some documentation in ./src/diffusers/models/embeddings.py for demo (#9579)
Daniel Regado (1):
[WIP] SD3.5 IP-Adapter Pipeline Integration (#9987)
Darshil Jariwala (1):
Add PAG Support for Stable Diffusion Inpaint Pipeline (#9386)
Dhruv Nair (18):
Improve downloads of sharded variants (#9869)
[CI] Unpin torch<2.5 in CI (#9961)
Flux latents fix (#9929)
[Single File] Fix SD3.5 single file loading (#10077)
[Single File] Pass token when fetching interpreted config (#10082)
[Single File] Add single file support for AutoencoderDC (#10183)
Fix format issue in push_test yml (#10235)
[Single File] Add GGUF support (#9964)
Fix Mochi Quality Issues (#10033)
Fix Doc links in GGUF and Quantization overview docs (#10279)
Make zeroing prompt embeds for Mochi Pipeline configurable (#10284)
[Single File] Add single file support for Flux Canny, Depth and Fill (#10288)
[Single File] Add single file support for Mochi Transformer (#10268)
Allow Mochi Transformer to be split across multiple GPUs (#10300)
[Single File] Add GGUF support for LTX (#10298)
Mochi docs (#9934)
[Single File] Add Single File support for HunYuan video (#10320)
[Single File] Fix loading (#10349)
Dimitri Barbot (2):
Update sdxl reference pipeline to latest sdxl pipeline (#9938)
Add sdxl controlnet reference community pipeline (#9893)
Dorsa Rohani (1):
Add Diffusion Policy for Reinforcement Learning (#9824)
Eliseu Silva (1):
Feature IP Adapter Xformers Attention Processor (#9881)
Emmanuel Benazera (1):
fix: missing AutoencoderKL lora adapter (#9807)
Ethan Smith (1):
fix min-snr implementation (#8466)
Fanli Lin (3):
fix bug in `require_accelerate_version_greater` (#9746)
make `pipelines` tests device-agnostic (part1) (#9399)
make `pipelines` tests device-agnostic (part2) (#9400)
Grant Sherrick (1):
Add server example (#9918)
Heavenn (1):
Modify apply_overlay for inpainting with padding_mask_crop (Inpainting area: "Only Masked") (#8793)
Ina (1):
[refactor] enhance readability of flux related pipelines (#9711)
Ivan Skorokhodov (1):
Use parameters + buffers when deciding upscale_dtype (#9882)
Jingya HUANG (1):
Add a doc for AWS Neuron in Diffusers (#9766)
Jonathan Yin (1):
Fix Nonetype attribute error when loading multiple Flux loras (#10182)
Juan Acevedo (2):
Update ptxla training (#9864)
add reshape to fix use_memory_efficient_attention in flax (#7918)
Junjie (1):
Add offload option in flux-control training (#10225)
Junsong Chen (4):
[DC-AE] Add the official Deep Compression Autoencoder code(32x,64x,128x compression ratio); (#9708)
[Sana] Add Sana, including `SanaPipeline`, `SanaPAGPipeline`, `LinearAttentionProcessor`, `Flow-based DPM-sovler` and so on. (#9982)
[Sana]add 2K related model for Sana (#10322)
[Sana bug] bug fix for 2K model config (#10340)
Kaiwen Sheng (1):
fix downsample bug in MidResTemporalBlock1D (#10250)
Leo Jiang (3):
[bugfix] bugfix for npu free memory (#9640)
NPU Adaption for FLUX (#9751)
Reduce Memory Cost in Flux Training (#9829)
Leojc (1):
docs: fix a mistake in docstring (#10319)
Linoy Tsaban (9):
[SD3-5 dreambooth lora] update model cards (#9749)
[SD 3.5 Dreambooth LoRA] support configurable training block & layers (#9762)
[flux dreambooth lora training] make LoRA target modules configurable + small bug fix (#9646)
[advanced flux training] bug fix + reduce memory cost as in #9829 (#9838)
[SD3 dreambooth lora] smol fix to checkpoint saving (#9993)
[Flux Redux] add prompt & multiple image input (#10056)
[community pipeline] Add RF-inversion Flux pipeline (#9816)
[community pipeline rf-inversion] - fix example in doc (#10179)
[RF inversion community pipeline] add eta_decay (#10199)
Lucain (1):
Let server decide default repo visibility (#10047)
Mehmet Yiğit Özgenç (1):
flux controlnet inpaint config bug (#10291)
Michael Tkachuk (1):
Enabling gradient checkpointing in eval() mode (#9878)
Miguel Farinha (1):
Allow image resolutions multiple of 8 instead of 64 in SVD pipeline (#6646)
Pakkapon Phongthawee (1):
add depth controlnet sd3 pre-trained checkpoints to docs (#9937)
Parag Ekbote (10):
Notebooks for Community Scripts Examples (#9905)
Move Wuerstchen Dreambooth to research_projects (#9935)
Fixed Nits in Docs and Example Script (#9940)
Notebooks for Community Scripts-2 (#9952)
Move IP Adapter Scripts to research project (#9960)
Notebooks for Community Scripts-3 (#10032)
Fixed Nits in Evaluation Docs (#10063)
Notebooks for Community Scripts-4 (#10094)
Fix Broken Link in Optimization Docs (#10105)
Fix Broken Links in ReadMe (#10117)
Pauline Bailly-Masson (1):
Ci update tpu (#10197)
Pedro Cuenca (2):
Interpolate fix on cuda for large output tensors (#10067)
Don't stale close-to-merge (#10096)
Qin Zhou (1):
Support pass kwargs to sd3 custom attention processor (#9818)
Rachit Shah (1):
config attribute not foud error for FluxImagetoImage Pipeline for multi controlnet solved (#9586)
Raul Ciotescu (1):
adds the pipeline for pixart alpha controlnet (#8857)
RogerSinghChugh (1):
Refac training utils.py (#9815)
SahilCarterr (9):
Added Support of Xlabs controlnet to FluxControlNetInpaintPipeline (#9770)
Fixes EMAModel "from_pretrained" method (#9779)
[Fix] Test of sd3 lora (#9843)
Updated _encode_prompt_with_clip and encode_prompt in train_dreamboth_sd3 (#9800)
[fix] Replaced shutil.copy with shutil.copyfile (#9885)
[FIX] Fix TypeError in DreamBooth SDXL when use_dora is False (#9879)
[Fix] Syntax error (#10068)
[FIX] Bug in FluxPosEmbed (#10115)
Added Error when len(gligen_images ) is not equal to len(gligen_phrases) in StableDiffusionGLIGENTextImagePipeline (#10176)
Sam (1):
Update pipeline_flux_img2img.py (#9928)
Sayak Paul (47):
post-release 0.31.0 (#9742)
Some minor updates to the nightly and push workflows (#9759)
[research_projects] add flux training script with quantization (#9754)
[research_projects] Update README.md to include a note about NF5 T5-xxl (#9775)
[CI] add new runner for testing (#9699)
[training] fixes to the quantization training script and add AdEMAMix optimizer as an option (#9806)
[training] use the lr when using 8bit adam. (#9796)
[Tests] clean up and refactor gradient checkpointing tests (#9494)
[CI] add a big GPU marker to run memory-intensive tests separately on CI (#9691)
[LoRA] fix: lora loading when using with a device_mapped model. (#9449)
[feat] add `load_lora_adapter()` for compatible models (#9712)
[Core] introduce `controlnet` module (#8768)
[Flux] reduce explicit device transfers and typecasting in flux. (#9817)
[Advanced LoRA v1.5] fix: gradient unscaling problem (#7018)
Revert "[Flux] reduce explicit device transfers and typecasting in flux." (#9896)
[LoRA] feat: `save_lora_adapter()` (#9862)
[LoRA] enable LoRA for Mochi-1 (#9943)
[Tests] skip nan lora tests on PyTorch 2.5.1 CPU. (#9975)
[Docs] add: missing pipelines from the spec. (#10005)
[Mochi-1] ensuring to compute the fourier features in FP32 in Mochi encoder (#10031)
[CI] Add quantization (#9832)
[tests] refactor vae tests (#9808)
[bitsandbytes] allow directly CUDA placements of pipelines loaded with bnb components (#9840)
[Tests] fix condition argument in xfail. (#10099)
[Tests] xfail incompatible SD configs. (#10127)
[LoRA] depcrecate save_attn_procs(). (#10126)
[LoRA] add a test to ensure `set_adapters()` and attn kwargs outs match (#10110)
[CI] merge peft pr workflow into the main pr workflow. (#10042)
[WIP][Training] Flux Control LoRA training script (#10130)
[Tests] update always test pipelines list. (#10143)
Update sana.md with minor corrections (#10232)
[docs] minor stuff to ltx video docs. (#10229)
[Docs] add rest of the lora loader mixins to the docs. (#10230)
[chore] add contribution note for lawrence. (#10253)
[LoRA] feat: lora support for SANA. (#10234)
[chore] fix: licensing headers in mochi and ltx (#10275)
[chore] fix: reamde -> readme (#10276)
[chore] Update README_sana.md to update the default model (#10285)
[LoRA] feat: support loading regular Flux LoRAs into Flux Control, and Fill (#10259)
[Tests] add integration tests for lora expansion stuff in Flux. (#10318)
[Docs] Update ltx_video.md to remove generator from `from_pretrained()` (#10316)
[Docs] Update gguf.md to remove generator from the pipeline from_pretrained (#10299)
[docs] fix: torchao example. (#10278)
[SANA LoRA] sana lora training tests and misc. (#10296)
[Tests] QoL improvements to the LoRA test suite (#10304)
[LoRA] test fix (#10351)
[Tests] Fix more tests sayak (#10359)
ScilenceForest (1):
Update train_controlnet_flux.py,Fix size mismatch issue in validation (#9679)
Shenghai Yuan (1):
[LoRA] Support HunyuanVideo (#10254)
SkyCol (1):
Add prompt about wandb in examples/dreambooth/readme. (#10014)
Soof Golan (1):
Improve post-processing performance (#10170)
Sookwan Han (1):
Add new community pipeline for 'Adaptive Mask Inpainting', introduced in [ECCV2024] ComA (#9228)
StAlKeR7779 (1):
DPM++ third order fixes (#9104)
Steven Liu (4):
[docs] load_lora_adapter (#10119)
[docs] Add missing AttnProcessors (#10246)
[docs] delete_adapters() (#10245)
[docs] Fix quantization links (#10323)
Thien Tran (1):
`.from_single_file()` - Add missing `.shape` (#10332)
Vahid Askari (1):
Fix: Remove duplicated comma in distributed_inference.md (#9868)
Vinh H. Pham (1):
[Fix] train_dreambooth_lora_flux_advanced ValueError: unexpected save model: <class 'transformers.models.t5.modeling_t5.T5EncoderModel'> (#9777)
Xinyuan Zhao (1):
Make `time_embed_dim` of `UNet2DModel` changeable (#10262)
YiYi Xu (6):
Revert "[LoRA] fix: lora loading when using with a device_mapped mode… (#9823)
fix controlnet module refactor (#9968)
Sd35 controlnet (#10020)
fix offloading for sd3.5 controlnets (#10072)
pass attn mask arg for flux (#10122)
update `get_parameter_dtype` (#10342)
Yu Zheng (1):
support sd3.5 for controlnet example (#9860)
Yuxuan.Zhang (1):
CogVideoX 1.5 (#9877)
Zhiyang Shen (1):
[Docs] fix docstring typo in SD3 pipeline (#9765)
_ (1):
Correct pipeline_output.py to the type Mochi (#9945)
aihao (1):
update (#7067)
cjkangme (2):
[Community Pipeline] Add some feature for regional prompting pipeline (#9874)
[Community Pipeline] Fix typo that cause error on regional prompting pipeline (#10251)
dg845 (1):
Enable Gradient Checkpointing for UNet2DModel (New) (#7201)
djm (1):
unet's `sample_size` attribute is to accept tuple(h, w) in `StableDiffusionPipeline` (#10181)
fancy45daddy (2):
add torch_xla support in pipeline_stable_audio.py (#10109)
Update pipeline_controlnet.py add support for pytorch_xla (#10222)
hlky (35):
Fix beta and exponential sigmas + add tests (#9954)
ControlNet from_single_file when already converted (#9978)
Add `beta`, `exponential` and `karras` sigmas to `FlowMatchEulerDiscreteScheduler` (#10001)
Add `sigmas` to Flux pipelines (#10081)
Fix `num_images_per_prompt>1` with Skip Guidance Layers in `StableDiffusion3Pipeline` (#10086)
Convert `sigmas` to `np.array` in FlowMatch set_timesteps (#10088)
Fix multi-prompt inference (#10103)
Test `skip_guidance_layers` in SD3 pipeline (#10102)
Fix `pipeline_stable_audio` formating (#10114)
Add `sigmas` to pipelines using FlowMatch (#10116)
Use `torch` in `get_3d_rotary_pos_embed`/`_allegro` (#10161)
Add ControlNetUnion (#10131)
Remove `negative_*` from SDXL callback (#10203)
refactor StableDiffusionXLControlNetUnion (#10200)
Use `torch` in `get_2d_sincos_pos_embed` and `get_3d_sincos_pos_embed` (#10156)
Use `t` instead of `timestep` in `_apply_perturbed_attention_guidance` (#10243)
Add `dynamic_shifting` to SD3 (#10236)
Fix `use_flow_sigmas` (#10242)
Fix ControlNetUnion _callback_tensor_inputs (#10218)
Use non-human subject in StableDiffusion3ControlNetPipeline example (#10214)
Add enable_vae_tiling to AllegroPipeline, fix example (#10212)
Fix checkpoint in CogView3PlusPipeline example (#10211)
Fix RePaint Scheduler (#10185)
Add ControlNetUnion to AutoPipeline from_pretrained (#10219)
Add `set_shift` to FlowMatchEulerDiscreteScheduler (#10269)
Use `torch` in `get_2d_rotary_pos_embed` (#10155)
Fix sigma_last with use_flow_sigmas (#10267)
Add Flux Control to AutoPipeline (#10292)
Check correct model type is passed to `from_pretrained` (#10189)
Fix `local_files_only` for checkpoints with shards (#10294)
Fix push_tests_mps.yml (#10326)
Fix EMAModel test_from_pretrained (#10325)
Support Flux IP Adapter (#10261)
Fix enable_sequential_cpu_offload in test_kandinsky_combined (#10324)
Fix FluxIPAdapterTesterMixin (#10354)
linjiapro (2):
Improve control net block index for sd3 (#9758)
Fix a bug for SD35 control net training and improve control net block index (#10065)
lsb (1):
Avoid compiling a progress bar. (#10098)
raulmosa (1):
Update handle single blocks on _convert_xlabs_flux_lora_to_diffusers (#9915)
sayakpaul (1):
Release: v0.32.0
skotapati (1):
Remove mps workaround for fp16 GELU, which is now supported natively (#10133)
suzukimain (1):
[community] Load Models from Sources like `Civitai` into Existing Pipelines (#9986)
zhangp365 (2):
Fix a bug in the state dict judgment in ip_adapter.py. (#10095)
fixed a dtype bfloat16 bug in torch_utils.py (#10125)
Álvaro Somoza (2):
[Official callbacks] SDXL Controlnet CFG Cutoff (#9311)
Change image_gen_aux repository URL (#10048)
ちくわぶ (1):
Add all AttnProcessor classes in `AttentionProcessor` type (#9909)
赵三石 (1):
Update lora_conversion_utils.py (#9980)
高佳宝 (1):
Update ip_adapter.py (#8882)
0 commit comments