AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-10-27 21:33:02 +03:00
Code Activity
1,477 Commits 933 Branches 102 Tags
v0.10.2-patch
Commit Graph

49 Commits

Author SHA1 Message Date
Patrick von Platen
315f37674b do not automatically enable xformers (#1640) 
* do not automatically enable xformers

* uP
 2022-12-09 18:30:36 +01:00
Ben Sherman
326de41915 Trivial fix for undefined symbol in train_dreambooth.py (#1598) 
easy fix for undefined name in train_dreambooth.py

import_model_class_from_model_name_or_path loads a pretrained model
and refers to args.revision in a context where args is undefined. I modified
the function to take revision as an argument and modified the invocation
of the function to pass in the revision from args. Seems like this was caused
by a cut and paste.
 2022-12-07 21:39:48 +01:00
Suraj Patil
9e1102990a [dreambooth] make collate_fn global (#1547) 
make collate_fn global
 2022-12-06 14:41:53 +01:00
Suraj Patil
c228331068 [examples] add check_min_version (#1550) 
* add check_min_version for examples

* move __version__ to the top

* Apply suggestions from code review

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* fix comment

* fix error_message

* adapt the install message

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-12-06 14:36:50 +01:00
Will Berman
af04479e85 [docs] [dreambooth training] default accelerate config (#1564) 2022-12-05 18:24:32 -08:00
Patrick von Platen
459b8ca81a Research folder (#1553) 
* Research folder

* Update examples/research_projects/README.md

* up
 2022-12-05 17:58:35 +01:00
Adalberto
e289998932 fix mask discrepancies in train_dreambooth_inpaint (#1529) 
The mask and instance image were being cropped in different ways without --center_crop, causing the model to learn to ignore the mask in some cases. This PR fixes that and generate more consistent results.
 2022-12-05 17:26:36 +01:00
Suraj Patil
634be6e53d [examples] use from_pretrained to load scheduler (#1549) 
us from_pretrained to load scheduler
 2022-12-05 15:32:24 +01:00
Adalberto
2b30b1090f Create train_dreambooth_inpaint.py (#1091) 
* Create train_dreambooth_inpaint.py

train_dreambooth.py adapted to work with the inpaint model, generating random masks during the training

* Update train_dreambooth_inpaint.py

refactored train_dreambooth_inpaint with black

* Update train_dreambooth_inpaint.py

* Update train_dreambooth_inpaint.py

* Update train_dreambooth_inpaint.py

Fix prior preservation

* add instructions to readme, fix SD2 compatibility
 2022-12-02 18:06:57 +01:00
Will Berman
25f850a23b [docs] [dreambooth training] num_class_images clarification (#1508) 2022-12-02 12:12:28 +01:00
Will Berman
b25ae2e6ab [docs] [dreambooth training] accelerate.utils.write_basic_config (#1513) 2022-12-02 12:11:18 +01:00
Patrick von Platen
1d4ad34af0 [Dreambooth] Make compatible with alt diffusion (#1470) 
* [Dreambooth] Make compatible with alt diffusion

* make style

* add example
 2022-11-30 13:48:17 +01:00
Suraj Patil
6c56f05097 v-prediction training support (#1455) 
* add get_velocity

* add v prediction for training

* fix saving

* add revision arg

* fix saving

* save checkpoints dreambooth

* fix saving embeds

* add instruction in readme

* quality

* noise_pred -> model_pred
 2022-11-28 17:46:54 +01:00
Suraj Patil
8b84f85192 [examples] fix mixed_precision arg (#1359) 
* use accelerator to check mixed_precision

* default `mixed_precision` to `None`

* pass mixed_precision to accelerate launch
 2022-11-22 13:35:23 +01:00
Patrick von Platen
195e437ac5 Correct path to schedlure (#1322) 
* [Examples] Correct path

* uP
 2022-11-18 12:32:49 +01:00
Glenn 'devalias' Grant
db1cb0b1a2 [dreambooth] link to bitsandbytes readme for installation (#1229) 
* add 'conda install cudatoolkit' to dreambooth 'training on 16GB' example 

fixes https://github.com/huggingface/diffusers/issues/1207

* Apply suggestions from code review

Co-authored-by: Suraj Patil <surajp815@gmail.com>
 2022-11-15 12:53:54 +01:00
camenduru
663f0c1963 [Flax] fix extra copy pasta 🍝 (#1187) 2022-11-09 11:34:15 +01:00
Yuta Hayashibe
555203e1fa Warning for invalid options without "--with_prior_preservation" (#1065) 
* Make errors for invalid options without "--with_prior_preservation"

* Make --instance_prompt required

* Removed needless check because --instance_data_dir is marked with required

* Updated messages

* Use logger.warning instead of raise errors

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-11-08 14:31:13 +01:00
Duong A. Nguyen
ac4c695d97 [Flax examples] Load text encoder from subfolder (#1147) 
load text encoder from subfolder
 2022-11-07 21:26:59 +01:00
Duong A. Nguyen
c62b3a2e7e [Flax] Fix sample batch size DreamBooth (#1129) 
fix sample batch size
 2022-11-04 13:49:57 +01:00
Yuta Hayashibe
33c487455e Fix padding in dreambooth (#1030) 2022-11-02 16:37:05 +01:00
Jonathan Rahn
0025626cd9 fix typo in examples dreambooth README.md (#1073) 
Update README.md

fixed typo
 2022-11-02 13:15:30 +01:00
Patrick von Platen
c18941b01a [Better scheduler docs] Improve usage examples of schedulers (#890) 
* [Better scheduler docs] Improve usage examples of schedulers

* finish

* fix warnings and add test

* finish

* more replacements

* adapt fast tests hf token

* correct more

* Apply suggestions from code review

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Integrate compatibility with euler

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-10-31 17:26:30 +01:00
Suraj Patil
eceeebdf91 Update train_dreambooth.py 2022-10-27 15:51:11 +02:00
Suraj Patil
52f2128dc6 update readme for flax examples (#1026) 2022-10-27 15:25:25 +02:00
Duong A. Nguyen
90f91adb0e [Flax] Add DreamBooth (#1001) 
* [Flax] Add DreamBooth

* fix sample rng

* style

* not reuse rng

* add dtype for mixed precision training

* Add Flax example
 2022-10-27 14:25:04 +02:00
Duong A. Nguyen
4623f095f3 [DreamBooth] Set train mode for text encoder (#1012) 
Set train mode for text encoder
 2022-10-27 14:19:13 +02:00
Suraj Patil
e92a603cab fix dreambooth script. (#1017) 
make input_args optional
 2022-10-27 11:44:06 +02:00
Brian Whicheloe
d3d22ce5a8 Small modification to enable usage by external scripts (#956) 
* Make training code usable by external scripts

Add parameter inputs to training and argument parsing function to allow this script to be used by an external call.

* Apply suggestions from code review

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-10-26 18:46:56 +02:00
Simon Kirsten
8332c1a6d9 Enable multi-process DataLoader for dreambooth (#950) 2022-10-26 17:24:48 +02:00
Yuta Hayashibe
4b9f58952a Add --pretrained_model_name_revision option to train_dreambooth.py (#933) 
* Add --pretrained_model_name_revision option to train_dreambooth.py

* Renamed --pretrained_model_name_revision to --revision
 2022-10-25 21:38:23 +02:00
Hanusz Leszek
4bf675f465 Dreambooth class image generation: using unique names to avoid overwriting existing image (#847) 
* Add an underscore to filename if it already exists

* Use sha1sum hash instead of adding underscores
 2022-10-20 15:56:15 +02:00
Suraj Patil
7674a36a34 [dreambooth] dont use safety check when generating prior images (#922) 
dont' use safety check when generating prior images
 2022-10-20 13:52:11 +02:00
Hanusz Leszek
ce7d96681c DOC Dreambooth Add --sample_batch_size=1 to the 8 GB dreambooth example script (#829) 
Add --sample_batch_size=1 to the 8 GB dreambooth script
 2022-10-20 13:44:37 +02:00
Suraj Patil
fbe807bf57 [dreambooth] allow fine-tuning text encoder (#883) 
* allow fine-tuning text encoder

* fix a few things

* update readme
 2022-10-18 17:28:51 +02:00
Omar Sanseviero
b8c4d5801c Remove unneeded use_auth_token (#839) 2022-10-14 13:27:03 +02:00
Anton Lozhkov
e001fededf Fix dreambooth loss type with prior_preservation and fp16 (#826) 
Fix dreambooth loss type with prior preservation
 2022-10-13 15:41:19 +02:00
spezialspezial
e895952816 Eventually preserve this typo? :) (#804) 2022-10-11 20:06:24 +02:00
Henrik Forstén
81bdbb5e2a DreamBooth DeepSpeed support for under 8 GB VRAM training (#735) 
* Support deepspeed

* Dreambooth DeepSpeed documentation

* Remove unnecessary casts, documentation

Due to recent commits some casts to half precision are not necessary
anymore.

Mention that DeepSpeed's version of Adam is about 2x faster.

* Review comments
 2022-10-10 21:29:27 +02:00
YaYaB
906e4105d7 Fix push_to_hub for dreambooth and textual_inversion (#748) 
* Fix push_to_hub for dreambooth and textual_inversion

* Use repo.push_to_hub instead of push_to_hub
 2022-10-07 11:50:28 +02:00
Patrick von Platen
4deb16e830 [Docs] Advertise fp16 instead of autocast (#740) 
up
 2022-10-05 22:20:53 +02:00
Suraj Patil
19e559d5e9 remove use_auth_token from remaining places (#737) 
remove use_auth_token
 2022-10-05 17:40:49 +02:00
Pierre LeMoine
08d4fb6e9f [dreambooth] Using already created Path in dataset (#681) 
using already created `Path` in dataset
 2022-10-05 12:14:30 +02:00
Yuta Hayashibe
7e92c5bc73 Fix typos (#718) 
* Fix typos

* Update examples/dreambooth/train_dreambooth.py

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2022-10-04 15:22:14 +02:00
Suraj Patil
14f4af8f5b [dreambooth] fix applying clip_grad_norm_ (#686) 
fix applying clip grad norm
 2022-10-03 10:54:01 +02:00
Suraj Patil
210be4fe71 [examples] update transfomers version (#665) 
update transfomrers version in example
 2022-09-29 11:16:28 +02:00
Suraj Patil
e5eed5235b [dreambooth] update install section (#650) 
update install section
 2022-09-27 17:32:21 +02:00
Suraj Patil
ac665b6484 [examples/dreambooth] don't pass tensor_format to scheduler. (#649) 
don't pass tensor_format
 2022-09-27 17:24:12 +02:00
Zhenhuan Liu
3b747de845 Add training example for DreamBooth. (#554) 
* Add training example for DreamBooth.

* Fix bugs.

* Update readme and default hyperparameters.

* Reformatting code with black.

* Update for multi-gpu trianing.

* Apply suggestions from code review

* improgve sampling

* fix autocast

* improve sampling more

* fix saving

* actuallu fix saving

* fix saving

* improve dataset

* fix collate fun

* fix collate_fn

* fix collate fn

* fix key name

* fix dataset

* fix collate fn

* concat batch in collate fn

* add grad ckpt

* add option for 8bit adam

* do two forward passes for prior preservation

* Revert "do two forward passes for prior preservation"

This reverts commit 661ca4677e.

* add option for prior_loss_weight

* add option for clip grad norm

* add more comments

* update readme

* update readme

* Apply suggestions from code review

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

* add docstr for dataset

* update the saving logic

* Update examples/dreambooth/README.md

* remove unused imports

Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2022-09-27 15:01:18 +02:00