GitLab

* Update textual_inversion.py

* Apply suggestions from code review

* Update textual_inversion.py

* Update textual_inversion.py

* Update textual_inversion.py

* Update textual_inversion.py

* Update examples/textual_inversion/textual_inversion.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update textual_inversion.py

* styling

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* standardize model card

* fix tags

* correct import styling and update tags

* run make style and make quality

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* post release

* style

* Empty-Commit

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Remove <cat-toy> validation prompt from examples/textual_inversion/textual_inversion_sdxl.py (#6877)

Remove <cat-toy> validation prompt from textual_inversion_sdxl.py

The `<cat-toy>` validation prompt is a default choice for the example task in the README. But no other part of `textual_inversion_sdxl.py` references the cat toy and `textual_inversion.py` has a default validation prompt of `None` as well.

So bring `textual_inversion_sdxl.py` in line with `textual_inversion.py` and change default validation prompt to `None`

change to 2024

* enable stable-xl textual inversion

* check if optimizer_2 exists

* check text_encoder_2 before using

* add textual inversion for sdxl in a single file

* fix style

* fix example style

* reset for error changes

* add readme for sdxl

* fix style

* disable autocast as it will cause cast error when weight_dtype=bf16

* fix spelling error

* fix style and readme and 8bit optimizer

* add README_sdxl.md link

* add tracker key on log_validation

* run style

* rm the second center crop

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* post release

* style

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Intel Gen 4 Xeon and later support bf16

* fix bf16 notes

* remove validation args from textual onverson tests

* reduce number of train steps in textual inversion tests

* fix: directories.

* debig

* fix: directories.

* remove validation tests from textual onversion

* try reducing the time of test_text_to_image_checkpointing_use_ema

* fix: directories

* speed up test_text_to_image_checkpointing

* speed up test_text_to_image_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints

* fix

* speed up test_instruct_pix2pix_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints

* set checkpoints_total_limit to 2.

* test_text_to_image_lora_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints speed up

* speed up test_unconditional_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints

* debug

* fix: directories.

* speed up test_instruct_pix2pix_checkpointing_checkpoints_total_limit

* speed up: test_controlnet_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints

* speed up test_controlnet_sdxl

* speed up dreambooth tests

* speed up test_dreambooth_lora_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints

* speed up test_custom_diffusion_checkpointing_checkpoints_total_limit_removes_multiple_checkpoints

* speed up test_text_to_image_lora_sdxl_text_encoder_checkpointing_checkpoints_total_limit

* speed up # checkpoint-2 should have been deleted

* speed up examples/text_to_image/test_text_to_image.py::TextToImage::test_text_to_image_checkpointing_checkpoints_total_limit

* additional speed ups

* style

Fix typos and trim trailing whitespaces

* Post Release: v0.24.0

* post pone deprecation

* post pone deprecation

* Add model_index.json

* control and custom diffusion

* dreambooth

* instructpix2pix and dreambooth ckpting

* t2i adapters.

* text to image ft

* textual inversion

* unconditional

* workflows

* import fix

* fix import

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* add variant

* add variant

* Apply suggestions from code review

* reformat

* fix: textual_inversion.py

* fix: variant in model_info

---------
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>

* post release

* fix: variant test

* up

* fix: test

post release

* Add Copyright info

* Fix typos, improve, update

* Update deepfloyd_if.md

* Update ldm3d_diffusion.md

* Update opt_overview.md

* fix: how print training resume logs.

* propagate changes to text-to-image scripts.

* propagate changes to instructpix2pix.

* propagate changes to dreambooth

* propagate changes to custom diffusion and instructpix2pix

* propagate changes to kandinsky

* propagate changes to textual inv.

* debug

* fix: checkpointing.

* debug

* debug

* debug

* back to the square

* debug

* debug

* change condition order.

* debug

* debug

* debug

* debug

* revert to original

* clean

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* [Release 0.21] Bump version

* fix & remove

* fix more

* fix all, upload

* Update textual_inversion.py

fixed safe_path bug in textual inversion training

* Update test_examples.py

update test_textual_inversion for updating saved file's name

* Update textual_inversion.py

fixed some formatting issues

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* make safetensors default

* set default save method as safetensors

* update tests

* update to support saving safetensors

* update test to account for safetensors default

* update example tests to use safetensors

* update example to support safetensors

* update unet tests for safetensors

* fix failing loader tests

* fix qc issues

* fix pipeline tests

* fix example test

---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* added placeholder token concatenation during training

* Update examples/textual_inversion/textual_inversion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* 0.20.0dev0

* make style

docs: Add missing import statement in textual_inversion inference instructions

* Multiply lr scheduler steps by `num_processes`.

* Stop multiplying steps by gradient accumulation.

* manual check for checkpoints_total_limit instead of using accelerate

* remove controlnet_conditioning_embedding_out_channels

* relax tolerance slightly

* correct incorrect naming

* Post release

* Post release

Apply deprecations

Expose num_cycles kwarg of get_schedule() through args.lr_num_cycles.

* Set --only_save_embeds to False by default

Due to how the option is named, it makes more sense to behave like this.

* Refactor only_save_embeds to save_as_full_pipeline

* Post release

* fix more

* Multi Vector

* Improve

* fix multi token

* improve test

* make style

* Update examples/test_examples.py

* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* update

* Finish

* Apply suggestions from code review

---------
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Update README.md

* Apply suggestions from code review