Skip to content

GitLab

Switch branch/tag
  1. 06 Feb, 2023 1 commit
  3. 03 Feb, 2023 3 commits
  5. 31 Jan, 2023 3 commits
  7. 27 Jan, 2023 1 commit
  9. 26 Jan, 2023 1 commit
  11. 25 Jan, 2023 4 commits
  13. 20 Jan, 2023 2 commits
  15. 19 Jan, 2023 2 commits
  17. 17 Jan, 2023 3 commits
    • Kashif Rasul's avatar
      DiT Pipeline (#1806) · 37d113cc
      Kashif Rasul authored 
      

* added dit model

* import

* initial pipeline

* initial convert script

* initial pipeline

* make style

* raise valueerror

* single function

* rename classes

* use DDIMScheduler

* timesteps embedder

* samples to cpu

* fix var names

* fix numpy type

* use timesteps class for proj

* fix typo

* fix arg name

* flip_sin_to_cos and better var names

* fix C shape cal

* make style

* remove unused imports

* cleanup

* add back patch_size

* initial dit doc

* typo

* Update docs/source/api/pipelines/dit.mdx
Co-authored-by: default avatarSuraj Patil <surajp815@gmail.com>

* added copyright license headers

* added example usage and toc

* fix variable names asserts

* remove comment

* added docs

* fix typo

* upstream changes

* set proper device for drop_ids

* added initial dit pipeline test

* update docs

* fix imports

* make fix-copies

* isort

* fix imports

* get rid of more magic numbers

* fix code when guidance is off

* remove block_kwargs

* cleanup script

* removed to_2tuple

* use FeedForward class instead of another MLP

* style

* work on mergint DiTBlock with BasicTransformerBlock

* added missing final_dropout and args to BasicTransformerBlock

* use norm from block

* fix arg

* remove unused arg

* fix call to class_embedder

* use timesteps

* make style

* attn_output gets multiplied

* removed commented code

* use Transformer2D

* use self.is_input_patches

* fix flags

* fixed conversion to use Transformer2DModel

* fixes for pipeline

* remove dit.py

* fix timesteps device

* use randn_tensor and fix fp16 inf.

* timesteps_emb already the right dtype

* fix dit test class

* fix test and style

* fix norm2 usage in vq-diffusion

* added author names to pipeline and lmagenet labels link

* fix tests

* use norm_type as string

* rename dit to transformer

* fix name

* fix test

* set  norm_type = "layer" by default

* fix tests

* do not skip common tests

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

* revert AdaLayerNorm API

* fix norm_type name

* make sure all components are in eval mode

* revert norm2 API

* compact

* finish deprecation

* add slow tests

* remove @

* refactor some stuff

* upload

* Update src/diffusers/pipelines/dit/pipeline_dit.py

* finish more

* finish docs

* improve docs

* finish docs
Co-authored-by: default avatarSuraj Patil <surajp815@gmail.com>
Co-authored-by: default avatarWilliam Berman <WLBberman@gmail.com>
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      37d113cc
    • Pedro Cuenca's avatar
      Check k-diffusion version is at least 0.0.12 (#2022) · 7e29b747
      Pedro Cuenca authored 
      * Check k-diffusion version is at least 0.0.12

* make style
      7e29b747
    • Jerry Jiarui XU's avatar
      [Flax] Add Flax inpainting impl (#1966) · a43bdd01
      Jerry Jiarui XU authored 
      * [Flax] Add Flax inpainting impl

* fixed copies, add README.md

* fixed README.md

* add test

* format

* update README.md
      a43bdd01
  19. 16 Jan, 2023 1 commit
  21. 13 Jan, 2023 1 commit
    • Vladimir Sotnikov's avatar
      [SD Img2Img] resize source images to multiple of 8 instead of 32 (#1571) · 9b37ed33
      Vladimir Sotnikov authored 
      

* [Stable Diffusion Img2Img] resize source images to integer multiple of 8 instead of 32

* [Alt Diffusion Img2Img] resize source images to multiple of 8 instead of 32

* [Img2Img] fix AltDiffusion Img2Img resolution test

* [Img2Img] add Stable Diffusion Img2Img resolution test

* [Cycle Diffusion] round resolution to multiplies of 8 instead of 32

* [ONNX SD Img2Img] round resolution to multiplies of 64 instead of 32

* [SD Depth2Img] round resolution to multiplies of 8 instead of 32

* [Repaint] round resolution to multiplies of 8 instead of 32

* fix make style
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      9b37ed33
  23. 12 Jan, 2023 1 commit
  25. 05 Jan, 2023 1 commit
  27. 04 Jan, 2023 1 commit
    • Patrick von Platen's avatar
      Improve reproduceability 2/3 (#1906) · 9b638548
      Patrick von Platen authored 
      * [Repro] Correct reproducability

* up

* up

* uP

* up

* need better image

* allow conversion from no state dict checkpoints

* up

* up

* up

* up

* check tensors

* check tensors

* check tensors

* check tensors

* next try

* up

* up

* better name

* up

* up

* Apply suggestions from code review

* correct more

* up

* replace all torch randn

* fix

* correct

* correct

* finish

* fix more

* up
      9b638548
  29. 03 Jan, 2023 1 commit
  31. 02 Jan, 2023 2 commits
  33. 30 Dec, 2022 1 commit
  35. 29 Dec, 2022 1 commit
    • Simon Kirsten's avatar
      Flax: Fix img2img and align with other pipeline (#1824) · ab0e92fd
      Simon Kirsten authored 
      

* Flax: Add components function

* Flax: Fix img2img and align with other pipeline

* Flax: Fix PRNGKey type

* Refactor strength to start_timestep

* Fix preprocess images

* Fix processed_images dimen

* latents.shape -> latents_shape

* Fix typo

* Remove "static" comment

* Remove unnecessary optional types in _generate

* Apply doc-builder code style.
Co-authored-by: default avatarPedro Cuenca <pedro@huggingface.co>
      ab0e92fd
  37. 25 Dec, 2022 1 commit
  39. 24 Dec, 2022 1 commit
  41. 20 Dec, 2022 2 commits
  43. 19 Dec, 2022 2 commits
  45. 17 Dec, 2022 2 commits
  47. 16 Dec, 2022 1 commit
  49. 15 Dec, 2022 1 commit