Skip to content

GitLab

Switch branch/tag
  1. 28 Feb, 2024 1 commit
  3. 23 Feb, 2024 1 commit
  5. 25 Sep, 2023 1 commit
  7. 11 Apr, 2023 1 commit
    • 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
  9. 27 Mar, 2023 1 commit
  11. 23 Mar, 2023 1 commit
  13. 17 Feb, 2023 1 commit
  15. 07 Feb, 2023 1 commit
  17. 06 Feb, 2023 1 commit
  19. 25 Jan, 2023 1 commit
  21. 09 Jan, 2023 1 commit
  23. 30 Dec, 2022 1 commit
  25. 19 Dec, 2022 1 commit
  27. 01 Dec, 2022 1 commit
    • fboulnois's avatar
      Standardize on using `image` argument in all pipelines (#1361) · 52eb0348
      fboulnois authored 
      * feat: switch core pipelines to use image arg

* test: update tests for core pipelines

* feat: switch examples to use image arg

* docs: update docs to use image arg

* style: format code using black and doc-builder

* fix: deprecate use of init_image in all pipelines
      52eb0348
  29. 17 Nov, 2022 1 commit
  31. 16 Nov, 2022 2 commits
  33. 07 Nov, 2022 1 commit
  35. 01 Nov, 2022 1 commit
    • MarkRich's avatar
      Add imagic to community pipelines (#958) · a793b1fe
      MarkRich authored 
      * initial commit to add imagic to stable diffusion community pipelines

* remove some testing changes

* comments from PR review for imagic stable diffusion

* remove changes from pipeline_stable_diffusion as part of imagic pipeline

* clean up example code and add line back in to pipeline_stable_diffusion for imagic pipeline

* remove unused functions

* small code quality changes for imagic pipeline

* clean up readme

* remove hardcoded logging values for imagic community example

* undo change for DDIMScheduler
      a793b1fe
  37. 29 Oct, 2022 1 commit
  39. 28 Oct, 2022 1 commit
  41. 27 Oct, 2022 2 commits
  43. 26 Oct, 2022 1 commit
    • 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
  45. 25 Oct, 2022 1 commit
  47. 24 Oct, 2022 1 commit
  49. 13 Oct, 2022 3 commits
  51. 11 Oct, 2022 2 commits
  53. 06 Oct, 2022 1 commit
    • Suraj Patil's avatar
      allow multiple generations per prompt (#741) · c119dc4c
      Suraj Patil authored 
      * compute text embeds per prompt

* don't repeat uncond prompts

* repeat separatly

* update image2image

* fix repeat uncond embeds

* adapt inpaint pipeline

* ifx uncond tokens in img2img

* add tests and fix ucond embeds in im2img and inpaint pipe
      c119dc4c
  55. 05 Oct, 2022 3 commits
  57. 04 Oct, 2022 1 commit
  59. 03 Oct, 2022 2 commits
  61. 02 Oct, 2022 1 commit
  63. 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