update to latest version #2

staoxiao · 2025-02-08T04:38:25Z

What does this PR do?

Fixes # (issue)

Before submitting

This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
Did you read the contributor guideline?
Did you read our philosophy doc (important for complex PRs)?
Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
Did you make sure to update the documentation with your changes? Here are the
documentation guidelines, and
here are tips on formatting docstrings.
Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

#10243)

* Add `dynamic_shifting` to SD3 * calculate_shift * FlowMatchHeunDiscreteScheduler doesn't support mu * Inpaint/img2img

use_flow_sigmas copy

…10214) * Use non-human subject in StableDiffusion3ControlNetPipeline example * make style

Fix repaint scheduler

* torchao quantizer --------- Co-authored-by: Sayak Paul <[email protected]> Co-authored-by: Steven Liu <[email protected]>

* attnprocessors * lora * make style * fix * fix * sana * typo

add contribution note for lawrence.

update

* add lora support for ltx * add tests * fix copied from comments * update --------- Co-authored-by: Sayak Paul <[email protected]>

update Co-authored-by: Sayak Paul <[email protected]>

* update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * Update src/diffusers/quantizers/gguf/utils.py Co-authored-by: Sayak Paul <[email protected]> * update * update * update * update * update * update * update * update * update * update * Update docs/source/en/quantization/gguf.md Co-authored-by: Steven Liu <[email protected]> * update * update * update * update --------- Co-authored-by: Sayak Paul <[email protected]> Co-authored-by: Steven Liu <[email protected]>

* update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * Update src/diffusers/models/transformers/transformer_mochi.py Co-authored-by: Aryan <[email protected]> --------- Co-authored-by: Sayak Paul <[email protected]> Co-authored-by: Aryan <[email protected]>

update

delete_adapters Co-authored-by: Sayak Paul <[email protected]>

…pipeline (#10251) fix: fix typo that cause error

* feat: lora support for SANA. * make fix-copies * rename test class. * attention_kwargs -> cross_attention_kwargs. * Revert "attention_kwargs -> cross_attention_kwargs." This reverts commit 23433bf. * exhaust 119 max line limit * sana lora fine-tuning script. * readme * add a note about the supported models. * Apply suggestions from code review Co-authored-by: Aryan <[email protected]> * style * docs for attention_kwargs. * remove lora_scale from pag pipeline. * copy fix --------- Co-authored-by: Aryan <[email protected]>

fix: licensing header.

* Use `torch` in `get_2d_rotary_pos_embed` * Add deprecation

fix: reamde -> readme

* Support pass kwargs to sd3 custom attention processor --------- Co-authored-by: hlky <[email protected]> Co-authored-by: YiYi Xu <[email protected]>

* flux_control_inpaint - failing test_flux_different_prompts * removing test_flux_different_prompts? * fix style * fix from PR comments * fix style * reducing guidance_scale in demo * Update src/diffusers/pipelines/flux/pipeline_flux_control_inpaint.py Co-authored-by: hlky <[email protected]> * make * prepare_latents is not copied from * update docs * typos --------- Co-authored-by: affromero <[email protected]> Co-authored-by: Sayak Paul <[email protected]> Co-authored-by: hlky <[email protected]>

…nputs (#10666)

* [training] Convert to ImageFolder script * make

#10663) controlnet union XL, make control_image immutible when this argument is passed a list, __call__ modifies its content, since it is pass by reference the list passed by the caller gets its content modified unexpectedly make a copy at method intro so this does not happen Co-authored-by: Teriks <[email protected]>

Co-authored-by: Giuseppe Catalano <[email protected]>

* start pyramid attention broadcast * add coauthor Co-Authored-By: Xuanlei Zhao <[email protected]> * update * make style * update * make style * add docs * add tests * update * Update docs/source/en/api/pipelines/cogvideox.md Co-authored-by: Steven Liu <[email protected]> * Update docs/source/en/api/pipelines/cogvideox.md Co-authored-by: Steven Liu <[email protected]> * Pyramid Attention Broadcast rewrite + introduce hooks (#9826) * rewrite implementation with hooks * make style * update * merge pyramid-attention-rewrite-2 * make style * remove changes from latte transformer * revert docs changes * better debug message * add todos for future * update tests * make style * cleanup * fix * improve log message; fix latte test * refactor * update * update * update * revert changes to tests * update docs * update tests * Apply suggestions from code review Co-authored-by: Steven Liu <[email protected]> * update * fix flux test * reorder * refactor * make fix-copies * update docs * fixes * more fixes * make style * update tests * update code example * make fix-copies * refactor based on reviews * use maybe_free_model_hooks * CacheMixin * make style * update * add current_timestep property; update docs * make fix-copies * update * improve tests * try circular import fix * apply suggestions from review * address review comments * Apply suggestions from code review * refactor hook implementation * add test suite for hooks * PAB Refactor (#10667) * update * update * update --------- Co-authored-by: DN6 <[email protected]> * update * fix remove hook behaviour --------- Co-authored-by: Xuanlei Zhao <[email protected]> Co-authored-by: Steven Liu <[email protected]> Co-authored-by: DN6 <[email protected]>

…de (#10600) * fix: refer to use_framewise_encoding on AutoencoderKLHunyuanVideo._encode * fix: comment about tile_sample_min_num_frames --------- Co-authored-by: Aryan <[email protected]>

* update * remove unused fn * apply suggestions based on review * update + cleanup 🧹 * more cleanup 🧹 * make fix-copies * update test

…_max_memory` (#10669) * conditionally check if compute capability is met. * log info. * fix condition. * updates * updates * updates * updates

…ity pipelines in float16 mode (#10670) Fix pipeline dtype unexpected change when using SDXL reference community pipelines

update llamatokenizer in hunyuanvideo tests

* support StableDiffusionAdapterPipeline.from_single_file * make style --------- Co-authored-by: Teriks <[email protected]> Co-authored-by: hlky <[email protected]>

fix_shape_error

* fix enable memory efficient attention on ROCm while calling CK implementation * Update attention_processor.py refactor of picking a set element

* Update train_instruct_pix2pix.py Fix inconsistent random transform in instruct_pix2pix * Update train_instruct_pix2pix_sdxl.py

…ity_for_timestep_sampling (#10699) * feat(training-utils): support device and dtype params in compute_density_for_timestep_sampling * chore: update type hint * refactor: use union for type hint --------- Co-authored-by: Sayak Paul <[email protected]>

Fix Doc Tutorial.

* fix dequantization for latest bnb. * smol fixes. * fix type annotation * update peft link * updates

* Fix Doc Tutorial. * Add 4 Notebooks and improve their example scripts.

…#10714) * Update pipeline_utils.py Added Self in from_pretrained method so inference will correctly recognize pipeline * Use typing_extensions --------- Co-authored-by: hlky <[email protected]>

Co-authored-by: hualxie <[email protected]>

* Added `auto_load_textual_inversion` and `auto_load_lora_weights` * update README.md * fix * make quality * Fix and `make style`

* NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * [bugfix]NPU Adaption for Sanna --------- Co-authored-by: J石页 <[email protected]> Co-authored-by: Sayak Paul <[email protected]>

hlky and others added 30 commits December 16, 2024 09:24

Use t instead of timestep in _apply_perturbed_attention_guidance (

672bd49

#10243)

Add dynamic_shifting to SD3 (#10236)

a7d5052

* Add `dynamic_shifting` to SD3 * calculate_shift * FlowMatchHeunDiscreteScheduler doesn't support mu * Inpaint/img2img

Fix use_flow_sigmas (#10242)

3f421fe

use_flow_sigmas copy

Fix ControlNetUnion _callback_tensor_inputs (#10218)

87e8157

Use non-human subject in StableDiffusion3ControlNetPipeline example (#…

438bd60

…10214) * Use non-human subject in StableDiffusion3ControlNetPipeline example * make style

Add enable_vae_tiling to AllegroPipeline, fix example (#10212)

7186bb4

Fix checkpoint in CogView3PlusPipeline example (#10211)

e9a3911

Fix RePaint Scheduler (#10185)

2f023d7

Fix repaint scheduler

Add ControlNetUnion to AutoPipeline from_pretrained (#10219)

5ed761a

fix downsample bug in MidResTemporalBlock1D (#10250)

aafed3f

[core] TorchAO Quantizer (#10009)

9f00c61

* torchao quantizer --------- Co-authored-by: Sayak Paul <[email protected]> Co-authored-by: Steven Liu <[email protected]>

[docs] Add missing AttnProcessors (#10246)

7667cfc

* attnprocessors * lora * make style * fix * fix * sana * typo

[chore] add contribution note for lawrence. (#10253)

6fb94d5

add contribution note for lawrence.

Fix copied from comment in Mochi lora loader (#10255)

0d96a89

update

[LoRA] Support LTX Video (#10228)

ac86393

* add lora support for ltx * add tests * fix copied from comments * update --------- Co-authored-by: Sayak Paul <[email protected]>

[docs] Clarify dtypes for Sana (#10248)

f9d5a93

update Co-authored-by: Sayak Paul <[email protected]>

[tests] Remove/rename unsupported quantization torchao type (#10263)

1524781

update

[docs] delete_adapters() (#10245)

2739241

delete_adapters Co-authored-by: Sayak Paul <[email protected]>

[Community Pipeline] Fix typo that cause error on regional prompting …

9c68c94

…pipeline (#10251) fix: fix typo that cause error

Add set_shift to FlowMatchEulerDiscreteScheduler (#10269)

ec1c7a7

[chore] fix: licensing headers in mochi and ltx (#10275)

ba6fd6e

fix: licensing header.

Use torch in get_2d_rotary_pos_embed (#10155)

0ac52d6

* Use `torch` in `get_2d_rotary_pos_embed` * Add deprecation

[chore] fix: reamde -> readme (#10276)

63cdf9c

fix: reamde -> readme

Make time_embed_dim of UNet2DModel changeable (#10262)

88b015d

Support pass kwargs to sd3 custom attention processor (#9818)

8eb73c8

* Support pass kwargs to sd3 custom attention processor --------- Co-authored-by: hlky <[email protected]> Co-authored-by: YiYi Xu <[email protected]>

Fix sigma_last with use_flow_sigmas (#10267)

e222246

hlky and others added 29 commits January 27, 2025 08:15

ControlNet Union controlnet_conditioning_scale for multiple control i…

18f7d1d

…nputs (#10666)

[training] Convert to ImageFolder script (#10664)

4157177

* [training] Convert to ImageFolder script * make

Add provider_options to OnnxRuntimeModel (#10661)

158c5c4

fix check_inputs func in LuminaText2ImgPipeline (#10651)

8ceec90

Revert RePaint scheduler 'fix' (#10644)

fb42066

Co-authored-by: Giuseppe Catalano <[email protected]>

[fix] refer use_framewise_encoding on AutoencoderKLHunyuanVideo._enco…

f295e2e

…de (#10600) * fix: refer to use_framewise_encoding on AutoencoderKLHunyuanVideo._encode * fix: comment about tile_sample_min_num_frames --------- Co-authored-by: Aryan <[email protected]>

Refactor gradient checkpointing (#10611)

c4d4ac2

* update * remove unused fn * apply suggestions based on review * update + cleanup 🧹 * more cleanup 🧹 * make fix-copies * update test

[Tests] conditionally check `fp8_e4m3_bf16_max_memory < fp8_e4m3_fp32…

7b100ce

…_max_memory` (#10669) * conditionally check if compute capability is met. * log info. * fix condition. * updates * updates * updates * updates

Fix pipeline dtype unexpected change when using SDXL reference commun…

196aef5

…ity pipelines in float16 mode (#10670) Fix pipeline dtype unexpected change when using SDXL reference community pipelines

[tests] update llamatokenizer in hunyuanvideo tests (#10681)

e6037e8

update llamatokenizer in hunyuanvideo tests

support StableDiffusionAdapterPipeline.from_single_file (#10552)

33f9361

* support StableDiffusionAdapterPipeline.from_single_file * make style --------- Co-authored-by: Teriks <[email protected]> Co-authored-by: hlky <[email protected]>

fix(hunyuan-video): typo in height and width input check (#10684)

ea76880

[FIX] check_inputs function in Auraflow Pipeline (#10678)

aad69ac

fix_shape_error

Fix enable memory efficient attention on ROCm (#10564)

1ae9b05

* fix enable memory efficient attention on ROCm while calling CK implementation * Update attention_processor.py refactor of picking a set element

Fix inconsistent random transform in instruct pix2pix (#10698)

5d2d239

* Update train_instruct_pix2pix.py Fix inconsistent random transform in instruct_pix2pix * Update train_instruct_pix2pix_sdxl.py

Fixed grammar in "write_own_pipeline" readme (#10706)

537891e

Fix Documentation about Image-to-Image Pipeline (#10704)

3e35f56

Fix Doc Tutorial.

[bitsandbytes] Simplify bnb int8 dequant (#10401)

5e8e6cb

* fix dequantization for latest bnb. * smol fixes. * fix type annotation * update peft link * updates

Fix train_text_to_image.py --help (#10711)

f63d322

Notebooks for Community Scripts-6 (#10713)

dbe0094

* Fix Doc Tutorial. * Add 4 Notebooks and improve their example scripts.

[Fix] Type Hint in from_pretrained() to Ensure Correct Type Inference (…

5b1dcd1

…#10714) * Update pipeline_utils.py Added Self in from_pretrained method so inference will correctly recognize pipeline * Use typing_extensions --------- Co-authored-by: hlky <[email protected]>

add provider_options in from_pretrained (#10719)

23bc56a

Co-authored-by: hualxie <[email protected]>

[Community] Enhanced Model Search (#10417)

145522c

* Added `auto_load_textual_inversion` and `auto_load_lora_weights` * update README.md * fix * make quality * Fix and `make style`

Quantized Flux with IP-Adapter (#10728)

d43ce14

EDMEulerScheduler accept sigmas, add final_sigmas_type (#10734)

464374f

staoxiao merged commit b0c6267 into staoxiao:main Feb 8, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

update to latest version #2

update to latest version #2

staoxiao commented Feb 8, 2025

update to latest version #2

update to latest version #2

Conversation

staoxiao commented Feb 8, 2025

What does this PR do?

Before submitting

Who can review?