e3f6ba3fc1
Merge branch 'main' into custom-code-updates
2025-08-11 11:55:57 +05:30
f442955c6e
[lora] support loading loras from lightx2v/Qwen-Image-Lightning ( #12119 )
...
* feat: support qwen lightning lora.
* add docs.
* fix
2025-08-11 09:27:10 +05:30
ff9a387618
[core] add modular support for Flux I2I ( #12086 )
...
* start
* encoder.
* up
* up
* up
* up
* up
* up
2025-08-11 07:23:23 +05:30
fb8722e9ab
update
2025-08-09 16:00:24 +02:00
512044c5ea
update
2025-08-09 15:06:18 +02:00
03c3f69aa5
[docs] diffusers gguf checkpoints ( #12092 )
...
* feat: support loading diffusers format gguf checkpoints.
* update
* update
* qwen
* up
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
* up
---------
Co-authored-by: DN6 <dhruv.nair@gmail.com >
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
2025-08-09 08:49:49 +05:30
f20aba3e87
[GGUF] feat: support loading diffusers format gguf checkpoints. ( #11684 )
...
* feat: support loading diffusers format gguf checkpoints.
* update
* update
* qwen
---------
Co-authored-by: DN6 <dhruv.nair@gmail.com >
2025-08-08 22:27:15 +05:30
6c85fcd899
update
2025-08-08 18:52:55 +02:00
085e9cba36
update
2025-08-08 18:22:44 +02:00
919ee1aee3
Merge branch 'main' into custom-code-updates
2025-08-08 19:53:30 +05:30
9cda45701c
Merge branch 'main' into custom-code-updates
2025-08-08 19:48:18 +05:30
c678e8a445
update
2025-08-08 19:47:50 +05:30
ccf2c31188
[Modular] Fast Tests ( #11937 )
...
* rearrage the params to groups: default params /image params /batch params / callback params
* make style
* add names property to pipeline blocks
* style
* remove more unused func
* prepare_latents_inpaint always return noise and image_latents
* up
* up
* update
* update
* update
* update
* update
* update
* update
* update
---------
Co-authored-by: DN6 <dhruv.nair@gmail.com >
2025-08-08 19:42:13 +05:30
d1342d7464
update
2025-08-08 12:10:06 +02:00
7b10e4ae65
[tests] device placement for non-denoiser components in group offloading LoRA tests ( #12103 )
...
up
2025-08-08 13:34:29 +05:30
3c0531bc50
lora_conversion_utils: replace lora up/down with a/b even if transformer. in key ( #12101 )
...
lora_conversion_utils: replace lora up/down with a/b even if transformer. in key
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-08-08 11:21:47 +05:30
a8e47978c6
[lora] adapt new LoRA config injection method ( #11999 )
...
* use state dict when setting up LoRA.
* up
* up
* up
* comment
* up
* up
2025-08-08 09:22:48 +05:30
50e18ee698
[qwen] device typo ( #12099 )
...
up
2025-08-07 12:27:39 -10:00
4b17fa2a2e
fix flux type hint ( #12089 )
...
fix-flux-type-hint
2025-08-07 13:00:15 +05:30
d45199a2f1
Implement Frequency-Decoupled Guidance (FDG) as a Guider ( #11976 )
...
* Initial commit implementing frequency-decoupled guidance (FDG) as a guider
* Update FrequencyDecoupledGuidance docstring to describe FDG
* Update project so that it accepts any number of non-batch dims
* Change guidance_scale and other params to accept a list of params for each freq level
* Add comment with Laplacian pyramid shapes
* Add function to import_utils to check if the kornia package is available
* Only import from kornia if package is available
* Fix bug: use pred_cond/uncond in freq space rather than data space
* Allow guidance rescaling to be done in data space or frequency space (speculative)
* Add kornia install instructions to kornia import error message
* Add config to control whether operations are upcast to fp64
* Add parallel_weights recommended values to docstring
* Apply style fixes
* make fix-copies
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co >
2025-08-07 11:21:02 +05:30
061163142d
[tests] tighten compilation tests for quantization ( #12002 )
...
* tighten compilation tests for quantization
* up
* up
2025-08-07 10:13:14 +05:30
5780776c8a
Make prompt_2 optional in Flux Pipelines ( #12073 )
...
* update
* update
2025-08-06 15:40:12 -10:00
f19421e27c
Helper functions to return skip-layer compatible layers ( #12048 )
...
update
Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com >
2025-08-06 07:55:16 -10:00
9a0cc463ee
update
2025-08-06 19:32:23 +02:00
ef4e373a65
Merge branch 'main' into custom-code-updates
2025-08-06 19:31:05 +02:00
1b4af6b7ef
update
2025-08-06 17:43:21 +02:00
69cdc25746
Fix group offloading synchronization bug for parameter-only GroupModule's ( #12077 )
...
* update
* update
* refactor
* fuck yeah
* make style
* Update src/diffusers/hooks/group_offloading.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* Update src/diffusers/hooks/group_offloading.py
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-08-06 21:11:00 +05:30
cfd6ec7465
[refactor] condense group offloading ( #11990 )
...
* update
* update
* refactor
* add test
* address review comment
* nit
2025-08-06 20:01:02 +05:30
ea77fdc4b4
update
2025-08-06 17:17:51 +05:30
1082c46afa
fix input shape for WanGGUFTexttoVideoSingleFileTests ( #12081 )
...
Signed-off-by: jiqing-feng <jiqing.feng@intel.com >
2025-08-06 14:12:40 +05:30
ba2ba9019f
Add cuda kernel support for GGUF inference ( #11869 )
...
* add gguf kernel support
Signed-off-by: Isotr0py <2037008807@qq.com >
* fix
Signed-off-by: Isotr0py <2037008807@qq.com >
* optimize
Signed-off-by: Isotr0py <2037008807@qq.com >
* update
* update
* update
* update
* update
---------
Signed-off-by: Isotr0py <2037008807@qq.com >
Co-authored-by: DN6 <dhruv.nair@gmail.com >
2025-08-05 21:36:48 +05:30
fa4c0e5e2e
optimize QwenImagePipeline to reduce unnecessary CUDA synchronization ( #12072 )
2025-08-05 04:12:47 -10:00
b793debd9d
[tests] deal with the failing AudioLDM2 tests ( #12069 )
...
up
2025-08-05 15:54:25 +05:30
377057126c
[tests] Fix Qwen test_inference slices ( #12070 )
...
update
2025-08-05 14:10:22 +05:30
5937e11d85
[docs] small corrections to the example in the Qwen docs ( #12068 )
...
* up
* up
2025-08-05 09:47:21 +05:30
9c1d4e3be1
[wip] feat: support lora in qwen image and training script ( #12056 )
...
* feat: support lora in qwen image and training script
* up
* up
* up
* up
* up
* up
* add lora tests
* fix
* add tests
* fix
* reviewer feedback
* up[
* Apply suggestions from code review
Co-authored-by: Aryan <aryan@huggingface.co >
---------
Co-authored-by: Aryan <aryan@huggingface.co >
2025-08-05 07:06:02 +05:30
7ea065c507
[docs] Install ( #12026 )
...
* initial
* init
2025-08-04 10:13:36 -07:00
7a7a487396
fix the rest for all GPUs in CI ( #12064 )
...
fix the rest
2025-08-04 21:03:33 +05:30
4efb4db9d0
enable all gpus when running ci. ( #12062 )
2025-08-04 20:17:34 +05:30
639fd12a20
CI fixing ( #12059 )
...
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-08-04 19:09:17 +05:30
69a9828f4d
fix(qwen-image): update vae license ( #12063 )
...
* fix(qwen-image):
- update vae license
* Apply style fixes
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co >
2025-08-04 17:08:47 +05:30
11d22e0e80
Cross attention module to Wan Attention ( #12058 )
...
* Cross attention module to Wan Attention
* Apply style fixes
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co >
2025-08-04 16:35:06 +05:30
9a38fab5ae
tests + minor refactor for QwenImage ( #12057 )
...
* update
* update
* update
* add docs
2025-08-04 16:28:42 +05:30
cb8e61ed2f
[wan2.2] follow-up ( #12024 )
...
* up
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-08-03 23:06:22 -10:00
8e53cd959e
Qwen-Image ( #12055 )
...
* (feat): qwen-image integration
* fix(qwen-image):
- remove unused logics related to controlnet/ip-adapter
* fix(qwen-image):
- compatible with attention dispatcher
- cond cache support
* fix(qwen-image):
- cond cache registry
- attention backend argument
- fix copies
* fix(qwen-image):
- remove local test
* Update src/diffusers/models/transformers/transformer_qwenimage.py
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2025-08-03 08:20:35 -10:00
359b605f4b
Update autoencoder_kl_cosmos.py ( #12045 )
...
* Update autoencoder_kl_cosmos.py
* Apply style fixes
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co >
2025-08-02 20:24:01 +05:30
6febc08bfc
Fix type of force_upcast to bool ( #12046 )
2025-08-02 19:03:13 +05:30
9a2eaed002
[LoRA] support lightx2v lora in wan ( #12040 )
...
* support lightx2v lora in wan
* add docsa.
* reviewer feedback
* empty
2025-08-02 11:43:26 +05:30
0c71189abe
Allow SD pipeline to use newer schedulers, eg: FlowMatch ( #12015 )
...
Allow SD pipeline to use newer schedulers, eg: FlowMatch,
by skipping attribute that doesnt exist there
(scale_model_input)
Lines starting
2025-07-31 23:59:40 -10:00
58d2b10a2e
[wan2.2] fix vae patches ( #12041 )
...
up
2025-07-31 23:43:42 -10:00
DN6