GitLab

add controlent script,

* add: utility for image grid.

* add: return type.

* change necessary places.

* add to utility page.

* Multiply lr scheduler steps by `num_processes`.

* Stop multiplying steps by gradient accumulation.

* avoid upcasting by assigning dtype to noise tensor

* make style

* Update train_unconditional.py

* Update train_unconditional.py

* make style

* add unit test for pickle

* revert change

---------
Co-authored-by: root <root@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Prathik Rao <prathikrao@microsoft.com@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>

* - Added validation parameters
- Changed some parameter descriptions to better explain their use.
- Fixed a few typos.
- Added concept_list parameter for better management of multiple subjects
- changed logic for image validation

* - Fixed bad logic for class data root directories

* Defaulting validation_steps to None for an easier logic

* Fixed multiple validation prompts

* Fixed bug on validation negative prompt

* Changed validation logic for tracker.

* Added uuid for validation image labeling

* Fix error when comparing validation prompts and validation negative prompts

* Improved error message when negative prompts for validation are more than the number of prompts

* - Changed image tracking number from epoch to global_step
- Added Typing for functions

* Added some validations more when using concept_list parameter and the regular ones.

* Fixed error message

* Added more validations for validation parameters

* Improved messaging for errors

* Fixed validation error for parameters with default values

* - Added train step to image name for validation
- reformatted code

* - Added train step to image's name for validation
- reformatted code

* Updated README.md file.

* reverted back original script of train_dreambooth.py

* reverted back original script of train_dreambooth.py

* left one blank line at the eof

* reverted back setup.py

* reverted back setup.py

* added same logic for when parameters for prior preservation are used without enabling the flag while using concept_list parameter.

* Ran black formatter.

* fixed a few strings

* fixed import sort with isort and removed fstrings without placeholder

* fixed import order with ruff (since with isort wasn't ok)

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

Apply deprecations

* update code to reflect latest changes as of May 30th

* update text to image example

* reflect changes to textual inversion

* make style

* fix typo

* Revert unnecessary readme changes

---------
Co-authored-by: root <root@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
Co-authored-by: Prathik Rao <prathikrao@microsoft.com@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>

cast to weight dtype

* 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>

* Added distillation for quantization example on textual inversion.
Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

* refined readme and code style.
Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

* Update text2images.py

* refined code of model load and added compatibility check.
Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

* fixed code style.
Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

* fix C403 [*] Unnecessary `list` comprehension (rewrite as a `set` comprehension)
Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

---------
Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>

* [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

use upload folder in training scripts
Co-authored-by: testbot <lucainp@hf.co>

* modify intel opts inference script

* modify readme

* modify doc

* fix some issues

* reformat

* reformat script

* format issue

* format issue

* Update train_text_to_image_lora.py

* Update train_text_to_image_lora.py

* Update train_text_to_image_lora.py

* Update train_text_to_image_lora.py

* format

The 'CLIPFeatureExtractor' class name has been renamed to 'CLIPImageProcessor' in order to comply with future deprecation. This commit includes the necessary changes to the affected files.

* updated black format

* update black format

* make style format

* updated line endings

* update code formatting

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

* Update src/diffusers/models/vae.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/models/vae.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* added vae gradient checkpointing test

* make style

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

* rename file

* rename attention

* fix more

* rename more

* up

* more deprecation imports

* fixes

* add lora

* Update examples/research_projects/lora/README.md

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

* Added multitoken training for textual inversion

* Updated assertion

* Removed duplicate save code

* Fixed undefined bug

* Fixed save

* Added multitoken clip model +util helper

* Removed code splitting

* Removed class

* Fixed errors

* Fixed errors

* Added loading functionality

* Loading via dict instead

* Fixed bug of invalid index being loaded

* Fixed adding placeholder token only adding 1 token

* Fixed bug when initializing tokens

* Fixed bug when initializing tokens

* Removed flawed logic

* Fixed vector shuffle

* Fixed tokenizer's inconsistent __call__ method

* Fixed tokenizer's inconsistent __call__ method

* Handling list input

* Added exception for adding invalid tokens to token map

* Removed unnecessary files and started working on progressive tokens

* Set at minimum load one token

* Changed to global step

* Added method to load automatic1111 tokens

* Fixed bug in load

* Quality+style fixes

* Update quality/style fixes

* Cast embeddings to fp16 when loading

* Fixed quality

* Started moving things over

* Clearing diffs

* Clearing diffs

* Moved everything

* Requested changes

* add total number checkpoints to training scripts

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

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

* Log Unconditional Image Generation Samples to WandB

* Check for wandb installation and parity between onnxruntime script

* Log epoch to wandb

* Check for tensorboard logger early on

* style fixes

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

Resolves ValueError: `num_inference_steps`: 1000 cannot be larger than `self.config.train_timesteps`: 50 as the unet model trained with this scheduler can only handle maximal 50 timesteps.

* before running make style

* remove left overs from flake8

* finish

* make fix-copies

* final fix

* more fixes

* Fix torchvision.transforms and transforms function naming clash

* Update unconditional script for onnx

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

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Add center crop and horizontal flip to args

* Update command to use center crop and random flip

* Add center crop and horizontal flip to args

* Update command to use center crop and random flip

* Create convert_vae_pt_to_diffusers.py

Just a simple script to convert VAE.pt files to diffusers format
Tested with: https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/VAEs/orangemix.vae.pt



* Update convert_vae_pt_to_diffusers.py

Forgot to add the function call

* make style

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

fix colossalai dreambooth

* refactor onnxruntime integration

* fix requirements.txt bug

* make style

* add support for textual_inversion

* make style

* add readme

* cleanup README files

* 1/27/2023 update to training scripts

* make style

* 1/30 update to train_unconditional

* style with black-22.8.0

---------
Co-authored-by: Prathik Rao <prathikrao@microsoft.com>
Co-authored-by: anton- <anton@huggingface.co>

* Create train_dreambooth_inpaint_lora.py

* Update train_dreambooth_inpaint_lora.py

* Update train_dreambooth_inpaint_lora.py

* Update train_dreambooth_inpaint_lora.py

* Update train_dreambooth_inpaint_lora.py