Skip to content

GitLab

Switch branch/tag
  1. 16 Apr, 2023 1 commit
  3. 14 Apr, 2023 2 commits
  5. 13 Apr, 2023 2 commits
  7. 12 Apr, 2023 4 commits
  9. 11 Apr, 2023 4 commits
    • Will Berman's avatar
      Attention processor cross attention norm group norm (#3021) · 98c5e5da
      Will Berman authored 
      add group norm type to attention processor cross attention norm

This lets the cross attention norm use both a group norm block and a
layer norm block.

The group norm operates along the channels dimension
and requires input shape (batch size, channels, *) where as the layer norm with a single
`normalized_shape` dimension only operates over the least significant
dimension i.e. (*, channels).

The channels we want to normalize are the hidden dimension of the encoder hidden states.

By convention, the encoder hidden states are always passed as (batch size, sequence
length, hidden states).

This means the layer norm can operate on the tensor without modification, but the group
norm requires flipping the last two dimensions to operate on (batch size, hidden states, sequence length).

All existing attention processors will have the same logic and we can
consolidate it in a helper function `prepare_encoder_hidden_states`

prepare_encoder_hidden_states -> norm_encoder_hidden_states re: @patrickvonplaten

move norm_cross defined check to outside norm_encoder_hidden_states

add missing attn.norm_cross check
      98c5e5da
    • Pedro Cuenca's avatar
      Fix scheduler type mismatch (#3041) · 526827c3
      Pedro Cuenca authored 
      When doing generation manually and using guidance_scale as a static
argument.
      526827c3
    • Will Berman's avatar
      config fixes (#3060) · 80bc0c0c
      Will Berman authored
      80bc0c0c
    • Patrick von Platen's avatar
      Fix config prints and save, load of pipelines (#2849) · 8b451eb6
      Patrick von Platen authored 
      * [Config] Fix config prints and save, load

* Only use potential nn.Modules for dtype and device

* Correct vae image processor

* make sure in_channels is not accessed directly

* make sure in channels is only accessed via config

* Make sure schedulers only access config attributes

* Make sure to access config in SAG

* Fix vae processor and make style

* add tests

* uP

* make style

* Fix more naming issues

* Final fix with vae config

* change more
      8b451eb6
  11. 06 Apr, 2023 1 commit
  13. 04 Apr, 2023 1 commit
  15. 31 Mar, 2023 4 commits
  17. 30 Mar, 2023 1 commit
  19. 28 Mar, 2023 5 commits
  21. 27 Mar, 2023 2 commits
  23. 24 Mar, 2023 3 commits
  25. 23 Mar, 2023 2 commits
  27. 22 Mar, 2023 1 commit
    • Patrick von Platen's avatar
      [MS Text To Video] Add first text to video (#2738) · ca1a2229
      Patrick von Platen authored 
      

* [MS Text To Video} Add first text to video

* upload

* make first model example

* match unet3d params

* make sure weights are correcctly converted

* improve

* forward pass works, but diff result

* make forward work

* fix more

* finish

* refactor video output class.

* feat: add support for a video export utility.

* fix: opencv availability check.

* run make fix-copies.

* add: docs for the model components.

* add: standalone pipeline doc.

* edit docstring of the pipeline.

* add: right path to TransformerTempModel

* add: first set of tests.

* complete fast tests for text to video.

* fix bug

* up

* three fast tests failing.

* add: note on slow tests

* make work with all schedulers

* apply styling.

* add slow tests

* change file name

* update

* more correction

* more fixes

* finish

* up

* Apply suggestions from code review

* up

* finish

* make copies

* fix pipeline tests

* fix more tests

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

* apply suggestions

* up

* revert

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
Co-authored-by: default avatarPedro Cuenca <pedro@huggingface.co>
      ca1a2229
  29. 21 Mar, 2023 1 commit
  31. 15 Mar, 2023 3 commits
  33. 14 Mar, 2023 1 commit
    • clarencechen's avatar
      Add support for different model prediction types in DDIMInverseScheduler (#2619) · ee71d9d0
      clarencechen authored 
      

* Add support for different model prediction types in DDIMInverseScheduler
Resolve alpha_prod_t_prev index issue for final step of inversion

* Fix old bug introduced when prediction type is "sample"

* Add support for sample clipping for numerical stability and deprecate old kwarg

* Detach sample, alphas, betas

Derive predicted noise from model output before dist. regularization

Style cleanup

* Log loss for debugging

* Revert "Log loss for debugging"

This reverts commit 76ea9c856f99f4c8eca45a0b1801593bb982584b.

* Add comments

* Add inversion equivalence test

* Add expected data for Pix2PixZero pipeline tests with SD 2

* Update tests/pipelines/stable_diffusion/test_stable_diffusion_pix2pix_zero.py

* Remove cruft and add more explanatory comments

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      ee71d9d0
  35. 13 Mar, 2023 2 commits