AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-10-23 09:09:01 +03:00
Code Activity
7,015 Commits 929 Branches 100 Tags
required-input-no-default
Commit Graph

291 Commits

Author SHA1 Message Date
YiYi Xu
b800f828f3 [docs] FLUX.3: modular-only notes, lazy loading, callbacks (#15069) 
* [docs] FLUX.3: modular-only notes, lazy loading, callbacks

Add a tips callout on what differs from DiffusionPipeline (lazy loading,
outputs, guider, offloading, editing blocks), move the prompting advice
into the upsampling section with the pop-the-step example, and add a
per-step callbacks section with a block that takes callback_on_step_end.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* [docs] FLUX.3: callback block walks all denoising loops

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* [docs] modular: add "Coming from DiffusionPipeline" to the quickstart and move per-step callbacks to the callbacks guide

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* [docs] FLUX.3: show the upsampled caption; clarify the index note in the quickstart

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* [docs] modular: make "Coming from DiffusionPipeline" its own page

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-16 13:34:11 -10:00
YiYi Xu
85c9fa4cae [cli] detect composite block classes in custom_blocks (#15001) 
`diffusers-cli custom_blocks` only recognized classes whose base was spelled
exactly `ModularPipelineBlocks`, so a `SequentialPipelineBlocks` or
`AutoPipelineBlocks` subclass (the usual thing to publish) was reported as
"could not be retrieved". Accept the composite subclasses as well, and match
on the class name so dotted bases like
`diffusers.modular_pipelines.SequentialPipelineBlocks` work too.

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-10 08:40:11 -10:00
Steven Liu
122b1e11fd [docs] Community methods (#14973) 
* freeu

* cachedit
 2026-10-07 08:04:42 -07:00
Sayak Paul
fef717ffb0 [core] propagate sage attention updates. (#14584) 
* propagate sage attention updates.

* add sage blackwell.

* up

* style.

* address feedback

* style.
 2026-09-29 18:47:23 +05:30
Sayak Paul
4ac08e9408 [diffusers-cli] add a dockerfile for diffusers cli hf jobs (#14550) 
* add a dockerfile for diffusers cli hf jobs

* up

* up

* use diffusers from pypi

* fix(ci): harden GitHub Actions workflows (#14550) (#14851)

fix(ci): harden workflow files flagged on #14550

Co-authored-by: hf-security-analysis[bot] <265538906+hf-security-analysis[bot]@users.noreply.github.com>

* Apply batched suggestions from code review

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* lower bound for tokenizers.

---------

Co-authored-by: hf-security-analysis[bot] <265538906+hf-security-analysis[bot]@users.noreply.github.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2026-09-29 16:50:36 +05:30
Steven Liu
4295ee3ec5 [docs] Adapters (#14842) 
* lora

* legacy adapters

* ip adapter

* controlnet

* feedback
 2026-09-24 09:11:42 -07:00
Sayak Paul
0121a91f9d test and docs for xet dedup based file sharing. (#14835) 
* test and docs for xet dedup based file sharing.

* up[
 2026-09-23 10:20:11 +05:30
Steven Liu
7263f3317f [docs] Using diffusion pipelines (#14805) 
* refactor

* more refactor

* improve diagram, fix link

* legacy ckpts
 2026-09-21 09:52:06 -07:00
Steven Liu
37ce5add81 [docs] Refactor get started section (#14783) 
* docs

* feedback

* feedback
 2026-09-17 08:06:40 -07:00
Steven Liu
b27b69c1d6 [docs] Improve navigation (#14537) 
* docs

* rearrange

* cross links

* titles
 2026-09-11 08:35:50 -07:00
Steven Liu
7a8c9da2a9 [CI] Repair broken links (#14627) 
fix

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-08-28 09:15:05 +05:30
kaixuanliu
b9bc22bd57 make examples in docs device agnostic (#14414) 
* docs: annotate hardcoded cuda device with alternatives in English docs

* docs: annotate hardcoded device_map="cuda" with alternatives

* update

Signed-off-by: kaixuanliu <kaixuan.liu@intel.com>

---------

Signed-off-by: kaixuanliu <kaixuan.liu@intel.com>
 2026-08-25 08:12:22 -07:00
Sayak Paul
9222edcce3 Deprecate 'fp16_safetensors' command in CLI documentation (#14583) 
Add deprecation notice for 'fp16_safetensors' command.
 2026-08-24 20:01:21 +05:30
Steven Liu
0eff7f0664 [docs] Clean up links (#14535) 
* docs

* more cleaning
 2026-08-20 08:18:52 -07:00
Dhruv Nair
3681e65996 Restructure skill files and reference guides for CLI based installation. (#14454) 
* restructure guides as skill references

* reorganize AGENTS.md and references

* clean up

* clean up

* clean up

* fix AGENTS.md references and add check_ai to Makefile

* clean up

* update paths

* clean up
 2026-08-20 18:16:49 +05:30
Dhruv Nair
f3175baf6a [CLI] Clean up and improvements to diffusers CLI (#14381) 
* [CLI] Clean up and improvements to `diffusers-cli`

Modular pipelines:
- `custom_blocks` also writes `modular_model_index.json`, so a packaged repo is
  loadable by `ModularPipeline.from_pretrained` (and runnable by `run`), not just
  importable as blocks.
- Add `--cpu-offload auto`, which offloads through the pipeline's
  `ComponentsManager`, plus `--offload-margin` to set its `memory_reserve_margin`.
- Add `--workflow` passthrough; warn and ignore it on standard pipelines.
- Route `model_index.json` repos whose `_class_name` is modular to the modular path.

Output saving:
- Resolve every media field on the output object (`images`, `frames`, `audios`,
  `audio`) instead of the first match, keeping the batch dimension. Fixes video
  output being misrouted through the image branch and LTX2's audio being dropped.
- Fix the `output_type="pt"` video transpose: `postprocess_video` returns
  `(B, F, C, H, W)`, not `(B, C, F, H, W)`.
- Save `(B, C, samples)` waveforms as multi-channel wavs (StableAudio).
- Write each video's frames to `<stem>-frames/<NNNN>.png`. Frames need no video
  backend, so they replace the `.pt` fallback when `export_to_video` fails.
- Report frame directories as a single path so hundreds of frames don't flood the
  terminal; `--push-to` and the sandbox download preserve subfolder structure.
- Raise on unrecognized payloads instead of dumping JSON/pickle.

Remote:
- Add `imageio`, `imageio-ffmpeg`, and `peft` to the default sandbox deps.
- Raise sandbox `start_timeout` to 600s; the 120s default expires while a cold node
  pulls the pytorch base image.

* Apply suggestion from @sayakpaul

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

* update

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-08-19 09:55:26 +05:30
Steven Liu
351de3a6fe [docs] deprecate torch_dtype for dtype (#14313) 
* docs

* update

* Revert "docs"

This reverts commit 04ca80543f.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-07-29 08:20:06 +05:30
Dhruv Nair
6afdfd9f4e Update diffusers-cli for agentic use (#13966) 
* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* pdate

* 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

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-07-22 17:02:44 +05:30
Sayak Paul
bc7aebc20a [core] deprecate dduf (#14141) 
* deprecate dduf (re-apply after accidental revert on main).

* up
 2026-07-16 13:24:12 +05:30
Sayak Paul
b8905b9b0f Revert "deprecate dduf." 
This reverts commit b3545f9c57.
 2026-07-08 07:21:41 +00:00
Sayak Paul
b3545f9c57 deprecate dduf. 2026-07-08 07:20:40 +00:00
Sayak Paul
c56add8081 post release v0.39.0 (#14116) 
* post release v0.39.0

* style.

* remove deprecated code path.

* remove deprecated method.
 2026-07-08 10:48:49 +05:30
Steven Liu
9a2923d501 [docs] remove pipeline examples section (#13771) 
* docs

* links
 2026-05-20 18:17:41 +09:00
Samuel Meddin
3e53a383e1 Fix typos and grammar errors in documentation (#13391) 
- Fix 'allows to generate' -> 'allows you to generate' in controlling_generation.md
- Fix 'it's refiner' -> 'its refiner' (possessive) in sdxl.md
- Fix 'it's state' -> 'its state' (possessive) in reusing_seeds.md
- Fix missing word 'you'll a function' -> 'you'll create a function' in sdxl.md
 2026-04-02 13:42:32 -07:00
Steven Liu
e365d749a1 [docs] deprecate pipelines (#13157) 
* deprecate

* fix

* fix

* fix

* fix

* remove deprecated .md files

* update links

* fix
 2026-04-01 10:16:23 -07:00
Steven Liu
ed31974c3e [docs] updates (#13248) 
* fixes

* few more links

* update zh

* fix
 2026-03-16 13:24:57 -07:00
Shenghai Yuan
ae5881ba77 Fix Helios paper link in documentation (#13213) 
* Fix Helios paper link in documentation

Updated the link to the Helios paper for accuracy.

* Fix reference link in HeliosTransformer3DModel documentation

Updated the reference link for the Helios Transformer model paper.

* Update Helios research paper link in documentation

* Update Helios research paper link in documentation
 2026-03-05 18:58:13 +05:30
dg845
33f785b444 Add Helios-14B Video Generation Pipelines (#13208) 
* [1/N] add helios

* fix test

* make fix-copies

* change script path

* fix cus script

* update docs

* fix documented check

* update links for docs and examples

* change default config

* small refactor

* add test

* Update src/diffusers/models/transformers/transformer_helios.py

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

* remove register_buffer for _scale_cache

* fix non-cuda devices error

* remove "handle the case when timestep is 2D"

* refactor HeliosMultiTermMemoryPatch and process_input_hidden_states

* Update src/diffusers/pipelines/helios/pipeline_helios.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/models/transformers/transformer_helios.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/pipelines/helios/pipeline_helios.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* fix calculate_shift

* Update src/diffusers/pipelines/helios/pipeline_helios.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* rewritten `einops` in pure `torch`

* fix: pass patch_size to apply_schedule_shift instead of hardcoding

* remove the logics of 'vae_decode_type'

* move some validation into check_inputs()

* rename helios scheduler & merge all into one step()

* add some details to doc

* move dmd  step() logics from pipeline to scheduler

* change to Python 3.9+ style type

* fix NoneType error

* refactor DMD scheduler's set_timestep

* change rope related vars name

* fix stage2 sample

* fix dmd sample

* Update src/diffusers/models/transformers/transformer_helios.py

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

* Update src/diffusers/models/transformers/transformer_helios.py

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

* remove redundant & refactor norm_out

* Update src/diffusers/pipelines/helios/pipeline_helios.py

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

* change "is_keep_x0" to "keep_first_frame"

* use a more intuitive name

* refactor dynamic_time_shifting

* remove use_dynamic_shifting args

* remove usage of UniPCMultistepScheduler

* separate stage2 sample to HeliosPyramidPipeline

* Update src/diffusers/models/transformers/transformer_helios.py

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

* Update src/diffusers/models/transformers/transformer_helios.py

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

* Update src/diffusers/models/transformers/transformer_helios.py

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

* Update src/diffusers/models/transformers/transformer_helios.py

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

* fix transformer

* use a more intuitive name

* update example script

* fix requirements

* remove redudant attention mask

* fix

* optimize pipelines

* make style .

* update TYPE_CHECKING

* change to use torch.split

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* derive memory patch sizes from patch_size multiples

* remove some hardcoding

* move some checks into check_inputs

* refactor sample_block_noise

* optimize encoding chunks logits for v2v

* use num_history_latent_frames = sum(history_sizes)

* Update src/diffusers/pipelines/helios/pipeline_helios.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* remove redudant optimized_scale

* Update src/diffusers/pipelines/helios/pipeline_helios_pyramid.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* use more descriptive name

* optimize history_latents

* remove not used "num_inference_steps"

* removed redudant "pyramid_num_stages"

* add "is_cfg_zero_star" and "is_distilled" to HeliosPyramidPipeline

* remove redudant

* change example scripts name

* change example scripts name

* correct docs

* update example

* update docs

* Update tests/models/transformers/test_models_transformer_helios.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update tests/models/transformers/test_models_transformer_helios.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* separate HeliosDMDScheduler

* fix numerical stability issue:

* Update src/diffusers/schedulers/scheduling_helios_dmd.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/schedulers/scheduling_helios_dmd.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/schedulers/scheduling_helios_dmd.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/schedulers/scheduling_helios_dmd.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/schedulers/scheduling_helios_dmd.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* remove redudant

* small refactor

* remove use_interpolate_prompt logits

* simplified model test

* fallbackt to BaseModelTesterConfig

* remove _maybe_expand_t2v_lora_for_i2v

* fix HeliosLoraLoaderMixin

* update docs

* use randn_tensor for test

* fix doc typo

* optimize code

* mark torch.compile xfail

* change paper name

* Make get_dummy_inputs deterministic using self.generator

* Set less strict threshold for test_save_load_float16 test for Helios pipeline

* make style and make quality

* Preparation for merging

* add torch.Generator

* Fix HeliosPipelineOutput doc path

* Fix Helios related (optimize docs & remove redudant) (#13210)

* fix docs

* remove redudant

* remove redudant

* fix group offload

* Removed fixes for group offload

---------

Co-authored-by: yuanshenghai <yuanshenghai@bytedance.com>
Co-authored-by: Shenghai Yuan <140951558+SHYuanBest@users.noreply.github.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: SHYuanBest <shyuan-cs@hotmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-03-04 21:31:43 +05:30
Dhruv Nair
3fd14f1acf [AutoModel] Allow registering auto_map to model config (#13186) 
* update

* update
 2026-03-02 22:13:25 +05:30
Dhruv Nair
bedc67c75f [Docs] Add guide for AutoModel with custom code (#13099) 
update
 2026-02-10 12:19:44 +05:30
Steven Liu
40de88af8c [docs] AutoModel (#12644) 
* automodel

* fix
 2025-11-13 08:43:24 -08:00
Ali Imran
1b456bd5d5 docs: cleanup of runway model (#12503) 
* cleanup of runway model

* quality fixes
 2025-10-17 14:10:50 -07:00
Steven Liu
b4e6dc3037 [docs] Fix broken links (#12487) 
fix broken links
 2025-10-15 06:42:10 +05:30
Steven Liu
3eb40786ca [docs] Prompting (#12312) 
* init

* fix

* batch inf

* feedback

* update
 2025-10-14 13:53:56 -07:00
Steven Liu
cc5b31ffc9 [docs] Migrate syntax (#12390) 
* change syntax

* make style
 2025-09-30 10:11:19 -07:00
Steven Liu
c07fcf780a [docs] Model formats (#12256) 
* init

* config

* lora metadata

* feedback

* fix

* cache allocator warmup for from_single_file

* feedback

* feedback
 2025-09-29 11:36:14 -07:00
Steven Liu
76810eca2b [docs] Schedulers (#12246) 
* init

* toctree

* scheduler suggestions

* toctree
 2025-09-23 10:29:16 -07:00
Sayak Paul
eb7ef26736 [quant] allow components_to_quantize to be a non-list for single components (#12234) 
* allow non list components_to_quantize.

* up

* Apply suggestions from code review

* Apply suggestions from code review

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* [docs] components_to_quantize (#12287)

init

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

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2025-09-10 09:47:08 -10:00
Steven Liu
fc337d5853 [docs] Models (#12248) 
* init

* fix

* feedback

* feedback
 2025-09-05 11:52:09 -07:00
Steven Liu
32798bf242 [docs] Inference section cleanup (#12281) 
init

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-09-05 09:34:37 -07:00
Steven Liu
c2e5ece08b [docs] Sharing pipelines/models (#12280) 
init
 2025-09-04 11:43:47 -07:00
Steven Liu
cbecc33570 [docs] Reproducibility (#12237) 
* init

* dupe

* feedback
 2025-08-27 11:35:31 -07:00
Steven Liu
5237a82a35 [docs] Remove Flax (#12244) 
* remove flax

* toctree

* feedback
 2025-08-27 11:11:07 -07:00
Manith Ratnayake
552c127c05 docs: correct typos in using-diffusers/other-formats (#12243) 2025-08-26 08:48:05 -07:00
Tianqi Tang
4b7fe044e3 Fix typos and inconsistencies (#12204) 
Fix typos and test assertions

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-08-26 07:58:08 -07:00
Steven Liu
2c4ee10b77 [docs] Diffusion pipeline (#12148) 
* init

* refactor

* refresh

* fix?

* fix?

* fix

* fix-copies

* feedback

* feedback

* fix

* feedback
 2025-08-25 11:06:12 -07:00
Steven Liu
b60faf456b [docs] Pipeline callbacks (#12212) 
* init

* review
 2025-08-22 13:01:24 -07:00
Steven Liu
3e73dc24a4 [docs] Community pipelines (#12201) 
* refresh

* feedback
 2025-08-22 10:42:13 -07:00
Steven Liu
421ee07e33 [docs] Parallel loading of shards (#12135) 
* initial

* feedback

* Update docs/source/en/using-diffusers/loading.md

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-08-14 09:39:40 +05:30
Steven Liu
c6fbcf717b [docs] Update toctree (#11936) 
* update

* fix

* feedback

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-07-18 13:37:04 -07:00