Skip to content

GitLab

Switch branch/tag
  1. 06 Jun, 2023 4 commits
  3. 05 Jun, 2023 1 commit
  5. 02 Jun, 2023 2 commits
    • Lachlan Nicholson's avatar
      Iterate over unique tokens to avoid duplicate replacements for multivector embeddings (#3588) · a6c7b5b6
      Lachlan Nicholson authored 
      * iterate over unique tokens to avoid duplicate replacements

* added test for multiple references to multi embedding

* adhere to black formatting

* reorder test post-rebase
      a6c7b5b6
    • Takuma Mori's avatar
      Support Kohya-ss style LoRA file format (in a limited capacity) (#3437) · 8e552bb4
      Takuma Mori authored 
      

* add _convert_kohya_lora_to_diffusers

* make style

* add scaffold

* match result: unet attention only

* fix monkey-patch for text_encoder

* with CLIPAttention

While the terrible images are no longer produced,
the results do not match those from the hook ver.
This may be due to not setting the network_alpha value.

* add to support network_alpha

* generate diff image

* fix monkey-patch for text_encoder

* add test_text_encoder_lora_monkey_patch()

* verify that it's okay to release the attn_procs

* fix closure version

* add comment

* Revert "fix monkey-patch for text_encoder"

This reverts commit bb9c61e6faecc1935c9c4319c77065837655d616.

* Fix to reuse utility functions

* make LoRAAttnProcessor targets to self_attn

* fix LoRAAttnProcessor target

* make style

* fix split key

* Update src/diffusers/loaders.py

* remove TEXT_ENCODER_TARGET_MODULES loop

* add print memory usage

* remove test_kohya_loras_scaffold.py

* add: doc on LoRA civitai

* remove print statement and refactor in the doc.

* fix state_dict test for kohya-ss style lora

* Apply suggestions from code review
Co-authored-by: default avatarTakuma Mori <takuma104@gmail.com>

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      8e552bb4
  7. 30 May, 2023 1 commit
  9. 26 May, 2023 2 commits
  11. 17 May, 2023 1 commit
  13. 11 May, 2023 1 commit
  15. 09 May, 2023 2 commits
    • Steven Liu's avatar
      [docs] Improve safetensors docstring (#3368) · 26832aa5
      Steven Liu authored 
      * clarify safetensor docstring

* fix typo

* apply feedback
      26832aa5
    • Will Berman's avatar
      if dreambooth lora (#3360) · a757b2db
      Will Berman authored 
      * update IF stage I pipelines

add fixed variance schedulers and lora loading

* added kv lora attn processor

* allow loading into alternative lora attn processor

* make vae optional

* throw away predicted variance

* allow loading into added kv lora layer

* allow load T5

* allow pre compute text embeddings

* set new variance type in schedulers

* fix copies

* refactor all prompt embedding code

class prompts are now included in pre-encoding code
max tokenizer length is now configurable
embedding attention mask is now configurable

* fix for when variance type is not defined on scheduler

* do not pre compute validation prompt if not present

* add example test for if lora dreambooth

* add check for train text encoder and pre compute text embeddings
      a757b2db
  17. 08 May, 2023 1 commit
    • pdoane's avatar
      Batched load of textual inversions (#3277) · 3d8b3d7c
      pdoane authored 
      

* Batched load of textual inversions

- Only call resize_token_embeddings once per batch as it is the most expensive operation
- Allow pretrained_model_name_or_path and token to be an optional list
- Remove Dict from type annotation pretrained_model_name_or_path as it was not supported in this function
- Add comment that single files (e.g. .pt/.safetensors) are supported
- Add comment for token parameter
- Convert token override log message from warning to info

* Update src/diffusers/loaders.py

Check for duplicate tokens
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>

* Update condition for None tokens

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      3d8b3d7c
  19. 28 Apr, 2023 1 commit
  21. 25 Apr, 2023 2 commits
  23. 20 Apr, 2023 2 commits
  25. 19 Apr, 2023 1 commit
  27. 12 Apr, 2023 2 commits
  29. 31 Mar, 2023 2 commits
  31. 30 Mar, 2023 1 commit
  33. 27 Mar, 2023 1 commit
  35. 16 Mar, 2023 1 commit
  37. 15 Mar, 2023 1 commit
  39. 14 Mar, 2023 1 commit
  41. 04 Mar, 2023 1 commit
  43. 03 Mar, 2023 1 commit
  45. 01 Mar, 2023 1 commit
  47. 27 Jan, 2023 1 commit
  49. 18 Jan, 2023 1 commit