Skip to content

GitLab

"src/vscode:/vscode.git/clone" did not exist on "d1db4f853a8d5da0a4bc4112010bca8d900871ef"
Switch branch/tag
  1. 03 Nov, 2022 1 commit
  3. 02 Nov, 2022 1 commit
  5. 31 Oct, 2022 2 commits
  7. 29 Oct, 2022 1 commit
  9. 27 Oct, 2022 1 commit
    • Pedro Cuenca's avatar
      Continuation of #942: additional float64 failure (#996) · 1d04e1b4
      Pedro Cuenca authored 
      * Add failing test for #940.

* Do not use torch.float64 in mps.

* style

* Temporarily skip add_noise for IPNDMScheduler.

Until #990 is addressed.

* Fix additional float64 error in mps.

* Improve add_noise test

* Slight edit – I think it's clearer this way.
      1d04e1b4
  11. 26 Oct, 2022 1 commit
  13. 25 Oct, 2022 2 commits
  15. 20 Oct, 2022 3 commits
  17. 18 Oct, 2022 1 commit
  19. 14 Oct, 2022 1 commit
  21. 13 Oct, 2022 1 commit
    • Suraj Patil's avatar
      update flax scheduler API (#822) · 0a09af2f
      Suraj Patil authored 
      * update flax scheduler API

* remoev set format

* fix call to scale_model_input

* update flax pndm

* use int32

* update docstr
      0a09af2f
  23. 10 Oct, 2022 1 commit
  25. 07 Oct, 2022 3 commits
  27. 06 Oct, 2022 4 commits
  29. 05 Oct, 2022 2 commits
  31. 04 Oct, 2022 1 commit
  33. 03 Oct, 2022 3 commits
    • Patrick von Platen's avatar
      [Utils] Add deprecate function and move testing_utils under utils (#659) · f1484b81
      Patrick von Platen authored 
      * [Utils] Add deprecate function

* up

* up

* uP

* up

* up

* up

* up

* uP

* up

* fix

* up

* move to deprecation utils file

* fix

* fix

* fix more
      f1484b81
    • Pedro Cuenca's avatar
      Fix import with Flax but without PyTorch (#688) · 688031c5
      Pedro Cuenca authored 
      * Don't use `load_state_dict` if torch is not installed.

* Define `SchedulerOutput` to use torch or flax arrays.

* Don't import LMSDiscreteScheduler without torch.

* Create distinct FlaxSchedulerOutput.

* Additional changes required for FlaxSchedulerMixin

* Do not import torch pipelines in Flax.

* Revert "Define `SchedulerOutput` to use torch or flax arrays."

This reverts commit f653140134b74d9ffec46d970eb46925fe3a409d.

* Prefix Flax scheduler outputs for consistency.

* make style

* FlaxSchedulerOutput is now a dataclass.

* Don't use f-string without placeholders.

* Add blank line.

* Style (docstrings)
      688031c5
    • Pedro Cuenca's avatar
      Flax: add shape argument to `set_timesteps` (#690) · 249b36cc
      Pedro Cuenca authored 
      * Flax: add shape argument to set_timesteps

* style
      249b36cc
  35. 30 Sep, 2022 1 commit
    • Nouamane Tazi's avatar
      Optimize Stable Diffusion (#371) · 9ebaea54
      Nouamane Tazi authored 
      * initial commit

* make UNet stream capturable

* try to fix noise_pred value

* remove cuda graph and keep NB

* non blocking unet with PNDMScheduler

* make timesteps np arrays for pndm scheduler
because lists don't get formatted to tensors in `self.set_format`

* make max async in pndm

* use channel last format in unet

* avoid moving timesteps device in each unet call

* avoid memcpy op in `get_timestep_embedding`

* add `channels_last` kwarg to `DiffusionPipeline.from_pretrained`

* update TODO

* replace `channels_last` kwarg with `memory_format` for more generality

* revert the channels_last changes to leave it for another PR

* remove non_blocking when moving input ids to device

* remove blocking from all .to() operations at beginning of pipeline

* fix merging

* fix merging

* model can run in other precisions without autocast

* attn refactoring

* Revert "attn refactoring"

This reverts commit 0c70c0e189cd2c4d8768274c9fcf5b940ee310fb.

* remove restriction to run conv_norm in fp32

* use `baddbmm` instead of `matmul`for better in attention for better perf

* removing all reshapes to test perf

* Revert "removing all reshapes to test perf"

This reverts commit 006ccb8a8c6bc7eb7e512392e692a29d9b1553cd.

* add shapes comments

* hardcore whats needed for jitting

* Revert "hardcore whats needed for jitting"

This reverts commit 2fa9c698eae2890ac5f8e367ca80532ecf94df9a.

* Revert "remove restriction to run conv_norm in fp32"

This reverts commit cec592890c32da3d1b78d38b49e4307aedf459b9.

* revert using baddmm in attention's forward

* cleanup comment

* remove restriction to run conv_norm in fp32. no quality loss was noticed

This reverts commit cc9bc1339c998ebe9e7d733f910c6d72d9792213.

* add more optimizations techniques to docs

* Revert "add shapes comments"

This reverts commit 31c58eadb8892f95478cdf05229adf678678c5f4.

* apply suggestions

* make quality

* apply suggestions

* styling

* `scheduler.timesteps` are now arrays so we dont need .to()

* remove useless .type()

* use mean instead of max in `test_stable_diffusion_inpaint_pipeline_k_lms`

* move scheduler timestamps to correct device if tensors

* add device to `set_timesteps` in LMSD scheduler

* `self.scheduler.set_timesteps` now uses device arg for schedulers that accept it

* quick fix

* styling

* remove kwargs from schedulers `set_timesteps`

* revert to using max in K-LMS inpaint pipeline test

* Revert "`self.scheduler.set_timesteps` now uses device arg for schedulers that accept it"

This reverts commit 00d5a51e5c20d8d445c8664407ef29608106d899.

* move timesteps to correct device before loop in SD pipeline

* apply previous fix to other SD pipelines

* UNet now accepts tensor timesteps even on wrong device, to avoid errors
- it shouldnt affect performance if timesteps are alrdy on correct device
- it does slow down performance if they're on the wrong device

* fix pipeline when timesteps are arrays with strides
      9ebaea54
  37. 29 Sep, 2022 1 commit
  39. 28 Sep, 2022 1 commit
  41. 27 Sep, 2022 5 commits
    • Kashif Rasul's avatar
      [Pytorch] add dep. warning for pytorch schedulers (#651) · 85494e88
      Kashif Rasul authored 
      * add dep. warning for schedulers

* fix format
      85494e88
    • Suraj Patil's avatar
      [DDIM, DDPM] fix add_noise (#648) · 33045382
      Suraj Patil authored 
      fix add noise
      33045382
    • Kashif Rasul's avatar
      [Pytorch] Pytorch only schedulers (#534) · bd8df2da
      Kashif Rasul authored 
      

* pytorch only schedulers

* fix style

* remove match_shape

* pytorch only ddpm

* remove SchedulerMixin

* remove numpy from karras_ve

* fix types

* remove numpy from lms_discrete

* remove numpy from pndm

* fix typo

* remove mixin and numpy from sde_vp and ve

* remove remaining tensor_format

* fix style

* sigmas has to be torch tensor

* removed set_format in readme

* remove set format from docs

* remove set_format from pipelines

* update tests

* fix typo

* continue to use mixin

* fix imports

* removed unsed imports

* match shape instead of assuming image shapes

* remove import typo

* update call to add_noise

* use math instead of numpy

* fix t_index

* removed commented out numpy tests

* timesteps needs to be discrete

* cast timesteps to int in flax scheduler too

* fix device mismatch issue

* small fix

* Update src/diffusers/schedulers/scheduling_pndm.py
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      bd8df2da
    • Pedro Cuenca's avatar
      Flax pipeline pndm (#583) · ab3fd671
      Pedro Cuenca authored 
      

* WIP: flax FlaxDiffusionPipeline & FlaxStableDiffusionPipeline

* todo comment

* Fix imports

* Fix imports

* add dummies

* Fix empty init

* make pipeline work

* up

* Allow dtype to be overridden on model load.

This may be a temporary solution until #567 is addressed.

* Convert params to bfloat16 or fp16 after loading.

This deals with the weights, not the model.

* Use Flax schedulers (typing, docstring)

* PNDM: replace control flow with jax functions.

Otherwise jitting/parallelization don't work properly as they don't know
how to deal with traced objects.

I temporarily removed `step_prk`.

* Pass latents shape to scheduler set_timesteps()

PNDMScheduler uses it to reserve space, other schedulers will just
ignore it.

* Wrap model imports inside availability checks.

* Optionally return state in from_config.

Useful for Flax schedulers.

* Do not convert model weights to dtype.

* Re-enable PRK steps with functional implementation.

Values returned still not verified for correctness.

* Remove left over has_state var.

* make style

* Apply suggestion list -> tuple
Co-authored-by: default avatarSuraj Patil <surajp815@gmail.com>

* Apply suggestion list -> tuple
Co-authored-by: default avatarSuraj Patil <surajp815@gmail.com>

* Remove unused comments.

* Use zeros instead of empty.
Co-authored-by: default avatarMishig Davaadorj <dmishig@gmail.com>
Co-authored-by: default avatarMishig Davaadorj <mishig.davaadorj@coloradocollege.edu>
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: default avatarSuraj Patil <surajp815@gmail.com>
      ab3fd671
    • Pedro Cuenca's avatar
      Remove inappropriate docstrings in LMS docstrings. (#634) · c070e5f0
      Pedro Cuenca authored
      c070e5f0
  43. 24 Sep, 2022 1 commit
  45. 22 Sep, 2022 1 commit
    • Jonathan Whitaker's avatar
      Adding pred_original_sample to SchedulerOutput for some samplers (#614) · 91db8189
      Jonathan Whitaker authored 
      * Adding pred_original_sample to SchedulerOutput of DDPMScheduler, DDIMScheduler, LMSDiscreteScheduler, KarrasVeScheduler step methods so we can access the predicted denoised outputs

* Gave DDPMScheduler, DDIMScheduler and LMSDiscreteScheduler their own output dataclasses so the default SchedulerOutput in scheduling_utils does not need pred_original_sample as an optional extra

* Reordered library imports to follow standard

* didnt get import order quite right apparently

* Forgot to change name of LMSDiscreteSchedulerOutput

* Aha, needed some extra libs for make style to fully work
      91db8189
  47. 21 Sep, 2022 1 commit