Daniel Socek
fbce7aeb32
Add generic support for Intel Gaudi accelerator (hpu device) ( #11328 )
...
* Add generic support for Intel Gaudi accelerator (hpu device)
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
Co-authored-by: Libin Tang <libin.tang@intel.com >
* Add loggers for generic HPU support
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
* Refactor hpu support with is_hpu_available() logic
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
* Fix style for hpu support update
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
* Decouple soft HPU check from hard device validation to support HPU migration
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
---------
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
Co-authored-by: Libin Tang <libin.tang@intel.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-04-30 14:45:02 +05:30
Yao Matrix
35fada4169
enable unidiffuser test cases on xpu ( #11444 )
...
* enable unidiffuser cases on XPU
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* fix a typo
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* fix style
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
---------
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
2025-04-30 13:58:00 +05:30
Yao Matrix
fbe2fe5578
enable consistency test cases on XPU, all passed ( #11446 )
...
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
2025-04-30 12:41:29 +05:30
Aryan
c86511586f
torch.compile fullgraph compatibility for Hunyuan Video (#11457 )
...
udpate
2025-04-30 11:21:17 +05:30
Yao Matrix
60892c55a4
enable marigold_intrinsics cases on XPU ( #11445 )
...
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
2025-04-30 11:07:37 +05:30
Aryan
8fe5a14d9b
Raise warning instead of error for block offloading with streams ( #11425 )
...
raise warning instead of error
2025-04-30 08:26:16 +05:30
Youlun Peng
58431f102c
Set LANCZOS as the default interpolation for image resizing in ControlNet training ( #11449 )
...
Set LANCZOS as the default interpolation for image resizing
2025-04-29 08:47:02 -04:00
urpetkov-amd
4a9ab650aa
Fixing missing provider options argument ( #11397 )
...
* Fixing missing provider options argument
* Adding if else for provider options
* Apply suggestions from code review
Co-authored-by: YiYi Xu <yixu310@gmail.com >
* Apply style fixes
* Update src/diffusers/pipelines/onnx_utils.py
Co-authored-by: YiYi Xu <yixu310@gmail.com >
* Update src/diffusers/pipelines/onnx_utils.py
Co-authored-by: YiYi Xu <yixu310@gmail.com >
---------
Co-authored-by: Uros Petkovic <urpektov@amd.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-04-28 10:23:05 -10:00
Linoy Tsaban
0ac1d5b482
[Hi-Dream LoRA] fix bug in validation ( #11439 )
...
remove unnecessary pipeline moving to cpu in validation
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-04-28 06:22:32 -10:00
Yao Matrix
7567adfc45
enable 28 GGUF test cases on XPU ( #11404 )
...
* enable gguf test cases on XPU
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
* make SD35LargeGGUFSingleFileTests::test_pipeline_inference pas
Signed-off-by: root <root@a4bf01945cfe.jf.intel.com >
* make FluxControlLoRAGGUFTests::test_lora_loading pass
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* polish code
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* Apply style fixes
---------
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
Signed-off-by: root <root@a4bf01945cfe.jf.intel.com >
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
Co-authored-by: root <root@a4bf01945cfe.jf.intel.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-04-28 21:32:04 +05:30
tongyu
3da98e7ee3
[train_text_to_image_lora] Better image interpolation in training scripts follow up ( #11427 )
...
* Update train_text_to_image_lora.py
* update_train_text_to_image_lora
2025-04-28 11:23:24 -04:00
tongyu
b3b04fefde
[train_text_to_image] Better image interpolation in training scripts follow up ( #11426 )
...
* Update train_text_to_image.py
* update
2025-04-28 10:50:33 -04:00
Sayak Paul
0e3f2713c2
[tests] fix import. ( #11434 )
...
fix import.
2025-04-28 13:32:28 +08:00
Yao Matrix
a7e9f85e21
enable test_layerwise_casting_memory cases on XPU ( #11406 )
...
* enable test_layerwise_casting_memory cases on XPU
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* fix style
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
---------
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
2025-04-28 06:38:39 +05:30
Yao Matrix
9ce89e2efa
enable group_offload cases and quanto cases on XPU ( #11405 )
...
* enable group_offload cases and quanto cases on XPU
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
* use backend APIs
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* fix style
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
---------
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
2025-04-28 06:37:16 +05:30
Sayak Paul
aa5f5d41d6
[tests] add tests to check for graph breaks, recompilation, cuda syncs in pipelines during torch.compile() ( #11085 )
...
* test for better torch.compile stuff.
* fixes
* recompilation and graph break.
* clear compilation cache.
* change to modeling level test.
* allow running compilation tests during nightlies.
2025-04-28 08:36:33 +08:00
Mert Erbak
bd96a084d3
[train_dreambooth_lora.py] Set LANCZOS as default interpolation mode for resizing ( #11421 )
...
* Set LANCZOS as default interpolation mode for resizing
* [train_dreambooth_lora.py] Set LANCZOS as default interpolation mode for resizing
2025-04-26 01:58:41 -04:00
co63oc
f00a995753
Fix typos in strings and comments ( #11407 )
2025-04-24 08:53:47 -10:00
Ishan Modi
e8312e7ca9
[BUG] fixed WAN docstring ( #11226 )
...
update
2025-04-24 08:49:37 -10:00
Emiliano
7986834572
Fix Flux IP adapter argument in the pipeline example ( #11402 )
...
Fix Flux IP adapter argument in the example
IP-Adapter example had a wrong argument. Fix `true_cfg` -> `true_cfg_scale`
2025-04-24 08:41:12 -10:00
Linoy Tsaban
edd7880418
[HiDream LoRA] optimizations + small updates ( #11381 )
...
* 1. add pre-computation of prompt embeddings when custom prompts are used as well
2. save model card even if model is not pushed to hub
3. remove scheduler initialization from code example - not necessary anymore (it's now if the base model's config)
4. add skip_final_inference - to allow to run with validation, but skip the final loading of the pipeline with the lora weights to reduce memory reqs
* pre encode validation prompt as well
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* pre encode validation prompt as well
* Apply style fixes
* empty commit
* change default trained modules
* empty commit
* address comments + change encoding of validation prompt (before it was only pre-encoded if custom prompts are provided, but should be pre-encoded either way)
* Apply style fixes
* empty commit
* fix validation_embeddings definition
* fix final inference condition
* fix pipeline deletion in last inference
* Apply style fixes
* empty commit
* layers
* remove readme remarks on only pre-computing when instance prompt is provided and change example to 3d icons
* smol fix
* empty commit
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-04-24 07:48:19 +03:00
Teriks
b4be42282d
Kolors additional pipelines, community contrib ( #11372 )
...
* Kolors additional pipelines, community contrib
---------
Co-authored-by: Teriks <Teriks@users.noreply.github.com >
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com >
2025-04-23 11:07:27 -10:00
Ishan Modi
a4f9c3cbc3
[Feature] Added Xlab Controlnet support ( #11249 )
...
update
2025-04-23 10:43:50 -10:00
Ishan Dutta
4b60f4b602
[train_dreambooth_flux] Add LANCZOS as the default interpolation mode for image resizing ( #11395 )
2025-04-23 10:47:05 -04:00
Aryan
6cef71de3a
Fix group offloading with block_level and use_stream=True ( #11375 )
...
* fix
* add tests
* add message check
2025-04-23 18:17:53 +05:30
Ameer Azam
026507c06c
Update README_hidream.md ( #11386 )
...
Small change
requirements_sana.txt to
requirements_hidream.txt
2025-04-22 20:08:26 -04:00
YiYi Xu
448c72a230
[HiDream] move deprecation to 0.35.0 ( #11384 )
...
up
2025-04-22 08:08:08 -10:00
Aryan
f108ad8888
Update modeling imports ( #11129 )
...
update
2025-04-22 06:59:25 -10:00
Linoy Tsaban
e30d3bf544
[LoRA] add LoRA support to HiDream and fine-tuning script ( #11281 )
...
* initial commit
* initial commit
* initial commit
* initial commit
* initial commit
* initial commit
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com >
* move prompt embeds, pooled embeds outside
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: hlky <hlky@hlky.ac >
* fix import
* fix import and tokenizer 4, text encoder 4 loading
* te
* prompt embeds
* fix naming
* shapes
* initial commit to add HiDreamImageLoraLoaderMixin
* fix init
* add tests
* loader
* fix model input
* add code example to readme
* fix default max length of text encoders
* prints
* nullify training cond in unpatchify for temp fix to incompatible shaping of transformer output during training
* smol fix
* unpatchify
* unpatchify
* fix validation
* flip pred and loss
* fix shift!!!
* revert unpatchify changes (for now)
* smol fix
* Apply style fixes
* workaround moe training
* workaround moe training
* remove prints
* to reduce some memory, keep vae in `weight_dtype` same as we have for flux (as it's the same vae)
bbd0c161b5/examples/dreambooth/train_dreambooth_lora_flux.py (L1207)spsayakpaul@gmail.com >
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* vae offload change
* fix text encoder offloading
* Apply style fixes
* cleaner to_kwargs
* fix module name in copied from
* add requirements
* fix offloading
* fix offloading
* fix offloading
* update transformers version in reqs
* try AutoTokenizer
* try AutoTokenizer
* Apply style fixes
* empty commit
* Delete tests/lora/test_lora_layers_hidream.py
* change tokenizer_4 to load with AutoTokenizer as well
* make text_encoder_four and tokenizer_four configurable
* save model card
* save model card
* revert T5
* fix test
* remove non diffusers lumina2 conversion
---------
Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com >
Co-authored-by: hlky <hlky@hlky.ac >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-04-22 11:44:02 +03:00
apolinário
6ab62c7431
Add stochastic sampling to FlowMatchEulerDiscreteScheduler ( #11369 )
...
* Add stochastic sampling to FlowMatchEulerDiscreteScheduler
This PR adds stochastic sampling to FlowMatchEulerDiscreteScheduler based on b1aeddd7ccyixu310@gmail.com >
* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py
Co-authored-by: YiYi Xu <yixu310@gmail.com >
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2025-04-21 17:18:30 -10:00
Ishan Modi
f59df3bb8b
[Refactor] Minor Improvement for import utils ( #11161 )
...
* update
* update
* addressed PR comments
* update
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2025-04-21 09:56:55 -10:00
josephrocca
a00c73a5e1
Support different-length pos/neg prompts for FLUX.1-schnell variants like Chroma ( #11120 )
...
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2025-04-21 09:28:19 -10:00
OleehyO
0434db9a99
[cogview4][feat] Support attention mechanism with variable-length support and batch packing ( #11349 )
...
* [cogview4] Enhance attention mechanism with variable-length support and batch packing
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-04-21 09:27:55 -10:00
Aamir Nazir
aff574fb29
Add Serialized Type Name kwarg in Model Output ( #10502 )
...
* Update outputs.py
2025-04-21 08:45:28 -10:00
Ishan Modi
79ea8eb258
[BUG] fixes in kadinsky pipeline ( #11080 )
...
* bug fix kadinsky pipeline
2025-04-21 08:41:09 -10:00
Aryan
e7f3a73786
Fix Wan I2V prepare_latents dtype ( #11371 )
...
update
2025-04-21 08:18:50 -10:00
PromeAI
7a4a126db8
fix issue that training flux controlnet was unstable and validation r… ( #11373 )
...
* fix issue that training flux controlnet was unstable and validation results were unstable
* del unused code pieces, fix grammar
---------
Co-authored-by: Your Name <you@example.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-04-21 08:16:05 -10:00
Kenneth Gerald Hamilton
0dec414d5b
[train_dreambooth_lora_sdxl.py] Fix the LR Schedulers when num_train_epochs is passed in a distributed training env ( #11240 )
...
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com >
2025-04-21 12:51:03 +05:30
Linoy Tsaban
44eeba07b2
[Flux LoRAs] fix lr scheduler bug in distributed scenarios ( #11242 )
...
* add fix
* add fix
* Apply style fixes
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-04-21 10:08:45 +03:00
YiYi Xu
5873377a66
[Wan2.1-FLF2V] update conversion script ( #11365 )
...
update scheuler config in conversion sript
2025-04-18 14:08:44 -10:00
YiYi Xu
5a2e0f715c
update output for Hidream transformer ( #11366 )
...
up
2025-04-18 14:07:21 -10:00
Kazuki Yoda
ef47726e2d
Fix: StableDiffusionXLControlNetAdapterInpaintPipeline incorrectly inherited StableDiffusionLoraLoaderMixin ( #11357 )
...
Fix: Inherit `StableDiffusionXLLoraLoaderMixin`
`StableDiffusionXLControlNetAdapterInpaintPipeline`
used to incorrectly inherit
`StableDiffusionLoraLoaderMixin`
instead of `StableDiffusionXLLoraLoaderMixin`
2025-04-18 12:46:06 -10:00
YiYi Xu
0021bfa1e1
support Wan-FLF2V ( #11353 )
...
* update transformer
---------
Co-authored-by: Aryan <aryan@huggingface.co >
2025-04-18 10:27:50 -10:00
Marc Sun
bbd0c161b5
[BNB] Fix test_moving_to_cpu_throws_warning ( #11356 )
...
fix
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-04-18 09:44:51 +05:30
Yao Matrix
eef3d65954
enable 2 test cases on XPU ( #11332 )
...
* enable 2 test cases on XPU
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
* Apply style fixes
---------
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2025-04-17 13:27:41 -10:00
Frank (Haofan) Wang
ee6ad51d96
Update controlnet_flux.py ( #11350 )
2025-04-17 10:05:01 -10:00
Sayak Paul
4397f59a37
[bitsandbytes] improve dtype mismatch handling for bnb + lora. ( #11270 )
...
* improve dtype mismatch handling for bnb + lora.
* add a test
* fix and updates
* update
2025-04-17 19:51:49 +05:30
YiYi Xu
056793295c
[Hi Dream] follow-up ( #11296 )
...
* add
2025-04-17 01:17:44 -10:00
Sayak Paul
29d2afbfe2
[LoRA] Propagate hotswap better ( #11333 )
...
* propagate hotswap to other load_lora_weights() methods.
* simplify documentations.
* updates
* propagate to load_lora_into_text_encoder.
* empty commit
2025-04-17 10:35:38 +05:30
Sayak Paul
b00a564dac
[docs] add note about use_duck_shape in auraflow docs. ( #11348 )
...
add note about use_duck_shape in auraflow docs.
2025-04-17 10:25:39 +05:30
