AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity
4,931 Commits 740 Branches 94 Tags
263b973466ea2abc88b579fc8f89bf366ce69c0f
Commit Graph

4931 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Sayak Paul
263b973466 [LoRA] feat: support loading loras into 4bit quantized Flux models. (#10578) 
* feat: support loading loras into 4bit quantized models.

* updates

* update

* remove weight check.
 2025-01-15 17:56:14 +05:30
Sayak Paul
a663a67ea2 [LoRA] clean up load_lora_into_text_encoder() and fuse_lora() copied from (#10495) 
* factor out text encoder loading.

* make fix-copies

* remove copied from fuse_lora and unfuse_lora as needed.

* remove unused imports
 2025-01-15 17:55:47 +05:30
Aryan
526858c801 [LoRA] Support original format loras for HunyuanVideo (#10376) 
* update

* fix make copies

* update

* add relevant markers to the integration test suite.

* add copied.

* fox-copies

* temporarily add print.

* directly place on CUDA as CPU isn't that big on the CIO.

* fixes to fuse_lora, aryan was right.

* fixes

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-15 17:55:40 +05:30
Sayak Paul
b3d2dd36d7 [LoRA] fix: lora unloading when using expanded Flux LoRAs. (#10397) 
* fix: lora unloading when using expanded Flux LoRAs.

* fix argument name.

Co-authored-by: a-r-r-o-w <contact.aryanvs@gmail.com>

* docs.

---------

Co-authored-by: a-r-r-o-w <contact.aryanvs@gmail.com>
 2025-01-15 17:55:19 +05:30
maxs-kan
abfa922410 Fix Flux multiple Lora loading bug (#10388) 
* check for base_layer key in transformer state dict

* test_lora_expansion_works_for_absent_keys

* check

* Update tests/lora/test_lora_layers_flux.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* check

* test_lora_expansion_works_for_absent_keys/test_lora_expansion_works_for_extra_keys

* absent->extra

---------

Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-01-15 17:55:05 +05:30
Sayak Paul
6a7b01f60f [LoRA] feat: support unload_lora_weights() for Flux Control. (#10206) 
* feat: support unload_lora_weights() for Flux Control.

* tighten test

* minor

* updates

* meta device fixes.
 2025-01-15 17:54:56 +05:30
Aryan
e8aacda762 Release: v0.32.1 v0.32.1 2024-12-25 11:34:06 +01:00
Aryan
12184f4015 Fix TorchAO related bugs; revert device_map changes (#10371) 
* Revert "Add support for sharded models when TorchAO quantization is enabled (#10256)"

This reverts commit 41ba8c0bf6.

* update tests

* udpate

* update

* update

* update device map tests

* apply review suggestions

* update

* make style

* fix

* update docs

* update tests

* update workflow

* update

* improve tests

* allclose tolerance

* Update src/diffusers/models/modeling_utils.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update tests/quantization/torchao/test_torchao.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* improve tests

* fix

* update correct slices

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-25 11:31:21 +01:00
Sayak Paul
6e1d2da194 fix test pypi installation in the release workflow (#10360) 
fix
 2024-12-25 11:25:34 +01:00
YiYi Xu
11b1151840 make style for https://github.com/huggingface/diffusers/pull/10368 (#10370) 
* fix bug for torch.uint1-7 not support in torch<2.6

* up

---------

Co-authored-by: baymax591 <cbai@mail.nwpu.edu.cn>
 2024-12-25 11:25:14 +01:00
sayakpaul
cd4d0d8ffb Release: v0.32.0 v0.32.0 2024-12-23 20:26:28 +05:30
Aryan
4b557132ce [core] LTX Video 0.9.1 (#10330) 
* update

* make style

* update

* update

* update

* make style

* single file related changes

* update

* fix

* update single file urls and docs

* update

* fix
 2024-12-23 19:51:33 +05:30
Sayak Paul
851dfa30ae [Tests] Fix more tests sayak (#10359) 
* fixes to tests

* fixture

* fixes
 2024-12-23 19:11:21 +05:30
Sayak Paul
ea1ba0ba53 [LoRA] test fix (#10351) 
updates
 2024-12-23 15:45:45 +05:30
Aryan
9d27df8071 Rename LTX blocks and docs title (#10213) 
* rename blocks and docs

* fix docs

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-23 15:29:10 +05:30
Aryan
055d95543a Fix failing CogVideoX LoRA fuse test (#10352) 
fix
 2024-12-23 14:22:09 +05:30
hlky
71cc2013fe Fix FluxIPAdapterTesterMixin (#10354) 2024-12-23 14:20:06 +05:30
Sayak Paul
c34fc34563 [Tests] QoL improvements to the LoRA test suite (#10304) 
* misc lora test improvements.

* updates

* fixes to tests
 2024-12-23 13:59:55 +05:30
Dhruv Nair
5fcee4a447 [Single File] Fix loading (#10349) 
update
 2024-12-23 13:12:23 +05:30
Sayak Paul
76e2727b5c [SANA LoRA] sana lora training tests and misc. (#10296) 
* sana lora training tests and misc.

* remove push to hub

* Update examples/dreambooth/train_dreambooth_lora_sana.py

Co-authored-by: Aryan <aryan@huggingface.co>

---------

Co-authored-by: Aryan <aryan@huggingface.co>
 2024-12-23 12:35:13 +05:30
Aryan
02c777c065 [tests] Refactor TorchAO serialization fast tests (#10271) 
refactor
 2024-12-23 11:04:57 +05:30
Sayak Paul
6a970a45c5 [docs] fix: torchao example. (#10278) 
fix: torchao example.
 2024-12-23 11:03:50 +05:30
Aryan
ffc0eaab6d Bump minimum TorchAO version to 0.7.0 (#10293) 
* bump min torchao version to 0.7.0

* update
 2024-12-23 11:03:04 +05:30
Thien Tran
3c2e2aa8a9 .from_single_file() - Add missing .shape (#10332) 
Add missing `.shape`
 2024-12-23 08:57:25 +05:30
Junsong Chen
b58868e6f4 [Sana bug] bug fix for 2K model config (#10340) 
* fix the Positinoal Embedding bug in 2K model;

* Change the default model to the BF16 one for more stable training and output

* make style

* substract buffer size

* add compute_module_persistent_sizes

---------

Co-authored-by: yiyixuxu <yixu310@gmail.com>
 2024-12-23 08:56:25 +05:30
Dhruv Nair
da21d590b5 [Single File] Add Single File support for HunYuan video (#10320) 
* update

* Update src/diffusers/loaders/single_file_utils.py

Co-authored-by: Aryan <aryan@huggingface.co>

---------

Co-authored-by: Aryan <aryan@huggingface.co>
 2024-12-23 08:44:58 +05:30
YiYi Xu
7c2f0afb1c update get_parameter_dtype (#10342) 
add:
q
 2024-12-23 08:14:13 +05:30
hlky
f615f00f58 Fix enable_sequential_cpu_offload in test_kandinsky_combined (#10324) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-22 15:28:28 -10:00
Aryan
6aaa0518e3 Community hosted weights for diffusers format HunyuanVideo weights (#10344) 
update docs and example to use community weights
 2024-12-22 15:26:28 -10:00
Mehmet Yiğit Özgenç
233dffdc3f flux controlnet inpaint config bug (#10291) 
* flux controlnet inpaint config bug

* Update src/diffusers/pipelines/flux/pipeline_flux_controlnet_inpainting.py

---------

Co-authored-by: yigitozgenc <yigit@quantuslabs.ai>
Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-21 18:44:43 +00:00
hlky
be2070991f Support Flux IP Adapter (#10261) 
* Flux IP-Adapter

* test cfg

* make style

* temp remove copied from

* fix test

* fix test

* v2

* fix

* make style

* temp remove copied from

* Apply suggestions from code review

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Move encoder_hid_proj to inside FluxTransformer2DModel

* merge

* separate encode_prompt, add copied from, image_encoder offload

* make

* fix test

* fix

* Update src/diffusers/pipelines/flux/pipeline_flux.py

* test_flux_prompt_embeds change not needed

* true_cfg -> true_cfg_scale

* fix merge conflict

* test_flux_ip_adapter_inference

* add fast test

* FluxIPAdapterMixin not test mixin

* Update pipeline_flux.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-21 17:49:58 +00:00
hlky
bf9a641f1a Fix EMAModel test_from_pretrained (#10325) 2024-12-21 14:10:44 +00:00
hlky
a756694bf0 Fix push_tests_mps.yml (#10326) 2024-12-21 14:10:32 +00:00
Sayak Paul
d41388145e [Docs] Update gguf.md to remove generator from the pipeline from_pretrained (#10299) 
Update gguf.md to remove generator from the pipeline from_pretrained
 2024-12-21 07:15:03 +05:30
Junsong Chen
a6288a5571 [Sana]add 2K related model for Sana (#10322) 
add 2K related model for Sana
 2024-12-20 07:21:34 -10:00
Steven Liu
7d4db57037 [docs] Fix quantization links (#10323) 
Update overview.md
 2024-12-20 08:30:21 -08:00
Aditya Raj
902008608a [BUG FIX] [Stable Audio Pipeline] Resolve torch.Tensor.new_zeros() TypeError in function prepare_latents caused by audio_vae_length (#10306) 
[BUG FIX] [Stable Audio Pipeline] TypeError: new_zeros(): argument 'size' failed to unpack the object at pos 3 with error "type must be tuple of ints,but got float"

torch.Tensor.new_zeros() takes a single argument size (int...) – a list, tuple, or torch.Size of integers defining the shape of the output tensor.

in function prepare_latents:
audio_vae_length = self.transformer.config.sample_size * self.vae.hop_length
audio_shape = (batch_size // num_waveforms_per_prompt, audio_channels, audio_vae_length)
...
audio = initial_audio_waveforms.new_zeros(audio_shape)

audio_vae_length evaluates to float because self.transformer.config.sample_size returns a float

Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-20 15:29:58 +00:00
Leojc
c8ee4af228 docs: fix a mistake in docstring (#10319) 
Update pipeline_hunyuan_video.py

docs: fix a mistake
 2024-12-20 15:22:32 +00:00
Sayak Paul
b64ca6c11c [Docs] Update ltx_video.md to remove generator from from_pretrained() (#10316) 
Update ltx_video.md to remove generator from `from_pretrained()`
 2024-12-20 18:32:22 +05:30
Dhruv Nair
e12d610faa Mochi docs (#9934) 
* update

* update

* update

* update

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-20 16:27:38 +05:30
Sayak Paul
bf6eaa8aec [Tests] add integration tests for lora expansion stuff in Flux. (#10318) 
add integration tests for lora expansion stuff in Flux.
 2024-12-20 16:14:58 +05:30
Sayak Paul
17128c42a4 [LoRA] feat: support loading regular Flux LoRAs into Flux Control, and Fill (#10259) 
* lora expansion with dummy zeros.

* updates

* fix working 🥳

* working.

* use torch.device meta for state dict expansion.

* tests

Co-authored-by: a-r-r-o-w <contact.aryanvs@gmail.com>

* fixes

* fixes

* switch to debug

* fix

* Apply suggestions from code review

Co-authored-by: Aryan <aryan@huggingface.co>

* fix stuff

* docs

---------

Co-authored-by: a-r-r-o-w <contact.aryanvs@gmail.com>
Co-authored-by: Aryan <aryan@huggingface.co>
 2024-12-20 14:30:32 +05:30
Dhruv Nair
dbc1d505f0 [Single File] Add GGUF support for LTX (#10298) 
* update

* add docs.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-20 11:52:29 +05:30
Aryan
151b74cd77 Make tensors in ResNet contiguous for Hunyuan VAE (#10309) 
contiguous tensors in resnet

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-20 11:45:37 +05:30
Aryan
41ba8c0bf6 Add support for sharded models when TorchAO quantization is enabled (#10256) 
* add sharded + device_map check
 2024-12-19 15:42:20 -10:00
Daniel Regado
3191248472 [WIP] SD3.5 IP-Adapter Pipeline Integration (#9987) 
* Added support for single IPAdapter on SD3.5 pipeline



---------

Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-19 14:48:18 -10:00
dg845
648d968cfc Enable Gradient Checkpointing for UNet2DModel (New) (#7201) 
* Port UNet2DModel gradient checkpointing code from #6718.


---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Vincent Neemie <92559302+VincentNeemie@users.noreply.github.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-19 14:45:45 -10:00
djm
b756ec6e80 unet's sample_size attribute is to accept tuple(h, w) in StableDiffusionPipeline (#10181) 2024-12-19 22:24:18 +00:00
Aryan
d8825e7697 Fix failing lora tests after HunyuanVideo lora (#10307) 
fix
 2024-12-20 02:35:41 +05:30
hlky
074798b299 Fix local_files_only for checkpoints with shards (#10294) 2024-12-19 07:04:57 -10:00