Skip to content

GitLab

Switch branch/tag
  1. 09 Nov, 2022 1 commit
  3. 08 Nov, 2022 4 commits
  5. 07 Nov, 2022 2 commits
  7. 06 Nov, 2022 1 commit
    • Cheng Lu's avatar
      Add multistep DPM-Solver discrete scheduler (#1132) · b4a1ed85
      Cheng Lu authored 
      

* add dpmsolver discrete pytorch scheduler

* fix some typos in dpm-solver pytorch

* add dpm-solver pytorch in stable-diffusion pipeline

* add jax/flax version dpm-solver

* change code style

* change code style

* add docs

* add `add_noise` method for dpmsolver

* add pytorch unit test for dpmsolver

* add dummy object for pytorch dpmsolver

* Update src/diffusers/schedulers/scheduling_dpmsolver_discrete.py
Co-authored-by: default avatarSuraj Patil <surajp815@gmail.com>

* Update tests/test_config.py
Co-authored-by: default avatarSuraj Patil <surajp815@gmail.com>

* Update tests/test_config.py
Co-authored-by: default avatarSuraj Patil <surajp815@gmail.com>

* resolve the code comments

* rename the file

* change class name

* fix code style

* add auto docs for dpmsolver multistep

* add more explanations for the stabilizing trick (for steps < 15)

* delete the dummy file

* change the API name of predict_epsilon, algorithm_type and solver_type

* add compatible lists
Co-authored-by: default avatarSuraj Patil <surajp815@gmail.com>
      b4a1ed85
  9. 04 Nov, 2022 2 commits
  11. 03 Nov, 2022 3 commits
    • Will Berman's avatar
      VQ-diffusion (#658) · ef2ea33c
      Will Berman authored 
      

* Changes for VQ-diffusion VQVAE

Add specify dimension of embeddings to VQModel:
`VQModel` will by default set the dimension of embeddings to the number
of latent channels. The VQ-diffusion VQVAE has a smaller
embedding dimension, 128, than number of latent channels, 256.

Add AttnDownEncoderBlock2D and AttnUpDecoderBlock2D to the up and down
unet block helpers. VQ-diffusion's VQVAE uses those two block types.

* Changes for VQ-diffusion transformer

Modify attention.py so SpatialTransformer can be used for
VQ-diffusion's transformer.

SpatialTransformer:
- Can now operate over discrete inputs (classes of vector embeddings) as well as continuous.
- `in_channels` was made optional in the constructor so two locations where it was passed as a positional arg were moved to kwargs
- modified forward pass to take optional timestep embeddings

ImagePositionalEmbeddings:
- added to provide positional embeddings to discrete inputs for latent pixels

BasicTransformerBlock:
- norm layers were made configurable so that the VQ-diffusion could use AdaLayerNorm with timestep embeddings
- modified forward pass to take optional timestep embeddings

CrossAttention:
- now may optionally take a bias parameter for its query, key, and value linear layers

FeedForward:
- Internal layers are now configurable

ApproximateGELU:
- Activation function in VQ-diffusion's feedforward layer

AdaLayerNorm:
- Norm layer modified to incorporate timestep embeddings

* Add VQ-diffusion scheduler

* Add VQ-diffusion pipeline

* Add VQ-diffusion convert script to diffusers

* Add VQ-diffusion dummy objects

* Add VQ-diffusion markdown docs

* Add VQ-diffusion tests

* some renaming

* some fixes

* more renaming

* correct

* fix typo

* correct weights

* finalize

* fix tests

* Apply suggestions from code review
Co-authored-by: default avatarAnton Lozhkov <aglozhkov@gmail.com>

* Apply suggestions from code review
Co-authored-by: default avatarPedro Cuenca <pedro@huggingface.co>

* finish

* finish

* up
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: default avatarAnton Lozhkov <aglozhkov@gmail.com>
Co-authored-by: default avatarPedro Cuenca <pedro@huggingface.co>
      ef2ea33c
    • Pedro Cuenca's avatar
      Continuation of #1035 (#1120) · 269109db
      Pedro Cuenca authored 
      

* remove batch size from repeat

* repeat empty string if uncond_tokens is none

* fix inpaint pipes

* return back whitespace to pass code quality

* Apply suggestions from code review

* Fix typos.
Co-authored-by: default avatarHad <had-95@yandex.ru>
      269109db
    • Revist's avatar
      feat: add repaint (#974) · d38c8043
      Revist authored 
      

* feat: add repaint

* fix: fix quality check with `make fix-copies`

* fix: remove old unnecessary arg

* chore: change default to DDPM (looks better in experiments)

* ".to(device)" changed to "device="
Co-authored-by: default avatarAnton Lozhkov <aglozhkov@gmail.com>

* make generator device-specific
Co-authored-by: default avatarAnton Lozhkov <aglozhkov@gmail.com>

* make generator device-specific and change shape
Co-authored-by: default avatarAnton Lozhkov <aglozhkov@gmail.com>

* fix: add preprocessing for image and mask
Co-authored-by: default avatarAnton Lozhkov <aglozhkov@gmail.com>

* fix: update test
Co-authored-by: default avatarAnton Lozhkov <aglozhkov@gmail.com>

* Update src/diffusers/pipelines/repaint/pipeline_repaint.py
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>

* Add docs and examples

* Fix toctree
Co-authored-by: default avatarfja <fja@zurich.ibm.com>
Co-authored-by: default avatarAnton Lozhkov <aglozhkov@gmail.com>
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: default avatarAnton Lozhkov <anton@huggingface.co>
      d38c8043
  13. 02 Nov, 2022 4 commits
    • Denis's avatar
      Training to predict x0 in training example (#1031) · cbcd0512
      Denis authored 
      

* changed training example to add option to train model that predicts x0 (instead of eps), changed DDPM pipeline accordingly

* Revert "changed training example to add option to train model that predicts x0 (instead of eps), changed DDPM pipeline accordingly"

This reverts commit c5efb525648885f2e7df71f4483a9f248515ad61.

* changed training example to add option to train model that predicts x0 (instead of eps), changed DDPM pipeline accordingly

* fixed code style
Co-authored-by: default avatarlukovnikov <lukovnikov@users.noreply.github.com>
      cbcd0512
    • Grigory Sizov's avatar
      Fix tests for equivalence of DDIM and DDPM pipelines (#1069) · 5cd29d62
      Grigory Sizov authored 
      * Fix equality test for ddim and ddpm

* add docs for use_clipped_model_output in DDIM

* fix inline comment

* reorder imports in test_pipelines.py

* Ignore use_clipped_model_output if scheduler doesn't take it
      5cd29d62
    • Patrick von Platen's avatar
      Rename latent (#1102) · d53ffbbd
      Patrick von Platen authored 
      * Rename latent

* uP
      d53ffbbd
    • MatthieuTPHR's avatar
      Up to 2x speedup on GPUs using memory efficient attention (#532) · 98c42134
      MatthieuTPHR authored 
      

* 2x speedup using memory efficient attention

* remove einops dependency

* Swap K, M in op instantiation

* Simplify code, remove unnecessary maybe_init call and function, remove unused self.scale parameter

* make xformers a soft dependency

* remove one-liner functions

* change one letter variable to appropriate names

* Remove Env variable dependency, remove MemoryEfficientCrossAttention class and use enable_xformers_memory_efficient_attention method

* Add memory efficient attention toggle to img2img and inpaint pipelines

* Clearer management of xformers' availability

* update optimizations markdown to add info about memory efficient attention

* add benchmarks for TITAN RTX

* More detailed explanation of how the mem eff benchmark were ran

* Removing autocast from optimization markdown

* import_utils: import torch only if is available
Co-authored-by: default avatarNouamane Tazi <nouamane98@gmail.com>
      98c42134
  15. 31 Oct, 2022 4 commits
  17. 30 Oct, 2022 1 commit
  19. 29 Oct, 2022 1 commit
  21. 28 Oct, 2022 1 commit
  23. 27 Oct, 2022 2 commits
  25. 26 Oct, 2022 2 commits
    • Hu Ye's avatar
      [inpaint pipeline] fix bug for multiple prompts inputs (#959) · bd06dd02
      Hu Ye authored
      bd06dd02
    • Pi Esposito's avatar
      minimal stable diffusion GPU memory usage with accelerate hooks (#850) · b2e2d141
      Pi Esposito authored 
      * add method to enable cuda with minimal gpu usage to stable diffusion

* add test to minimal cuda memory usage

* ensure all models but unet are onn torch.float32

* move to cpu_offload along with minor internal changes to make it work

* make it test against accelerate master branch

* coming back, its official: I don't know how to make it test againt the master branch from accelerate

* make it install accelerate from master on tests

* go back to accelerate>=0.11

* undo prettier formatting on yml files

* undo prettier formatting on yml files againn
      b2e2d141
  27. 25 Oct, 2022 6 commits
  29. 24 Oct, 2022 2 commits
  31. 21 Oct, 2022 1 commit
    • mkshing's avatar
      Support LMSDiscreteScheduler in LDMPipeline (#891) · 31af4d17
      mkshing authored 
      

* Support LMSDiscreteScheduler in LDMPipeline

This is a small change to support all schedulers such as LMSDiscreteScheduler in LDMPipeline.

What's changed
-------
* Add the `scale_model_input` function before `step` to ensure correct denoising (L77)

* Add "scale the initial noise by the standard deviation required by the scheduler"

* run `make style`
Co-authored-by: default avatarAnton Lozhkov <anton@huggingface.co>
      31af4d17
  33. 19 Oct, 2022 3 commits