AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity
1,979 Commits 740 Branches 94 Tags
a72d14fc8d36c442e449ee032ef55478a5dd11f0
Commit Graph

354 Commits

Author SHA1 Message Date
Henrik Forstén
79eb3d07d0 Controlnet training (#2545) 
* Controlnet training code initial commit

Works with circle dataset: https://github.com/lllyasviel/ControlNet/blob/main/docs/train.md

* Script for adding a controlnet to existing model

* Fix control image transform

Control image should be in 0..1 range.

* Add license header and remove more unused configs

* controlnet training readme

* Allow nonlocal model in add_controlnet.py

* Formatting

* Remove unused code

* Code quality

* Initialize controlnet in training script

* Formatting

* Address review comments

* doc style

* explicit constructor args and submodule names

* hub dataset

NOTE -  not tested

* empty prompts

* add conditioning image

* rename

* remove instance data dir

* image_transforms -> -1,1 . conditioning_image_transformers -> 0, 1

* nits

* remove local rank config

I think this isn't necessary in any of our training scripts

* validation images

* proportion_empty_prompts typo

* weight copying to controlnet bug

* call log validation fix

* fix

* gitignore wandb

* fix progress bar and resume from checkpoint iteration

* initial step fix

* log multiple images

* fix

* fixes

* tracker project name configurable

* misc

* add controlnet requirements.txt

* update docs

* image labels

* small fixes

* log validation using existing models for pipeline

* fix for deepspeed saving

* memory usage docs

* Update examples/controlnet/train_controlnet.py

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

* Update examples/controlnet/train_controlnet.py

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

* Update examples/controlnet/README.md

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

* Update examples/controlnet/README.md

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

* Update examples/controlnet/README.md

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

* Update examples/controlnet/README.md

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

* Update examples/controlnet/README.md

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

* Update examples/controlnet/README.md

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

* Update examples/controlnet/README.md

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

* Update examples/controlnet/README.md

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

* remove extra is main process check

* link to dataset in intro paragraph

* remove unnecessary paragraph

* note on deepspeed

* Update examples/controlnet/README.md

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

* assert -> value error

* weights and biases note

* move images out of git

* remove .gitignore

---------

Co-authored-by: William Berman <WLBberman@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-03-14 20:16:30 -07:00
aengusng8
268ebcb015 Add ddim noise comparative analysis pipeline (#2665) 
* add DDIM Noise Comparative Analysis pipeline

* update README

* add comments

* run BLACK format
 2023-03-14 18:09:55 +01:00
Will Berman
ebd44957fc image generation main process checks (#2631) 2023-03-14 01:28:03 -07:00
Ruizhe Wang
ce08cb72fb [Dreambooth] Editable number of class images (#2251) 
* [Dreambooth] Editable number of class images

* 'class_num=None' bug fix

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-03-10 14:15:16 +01:00
Patrick von Platen
cbbad0af69 correct example 2023-03-08 20:14:19 +01:00
Haofan Wang
00132de359 Support LoRA for text encoder (#2588) 
* add lora

* Update examples/research_projects/lora/README.md

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-03-08 20:14:01 +01:00
Michael Gartsbein
46bef6e31d community stablediffusion controlnet img2img pipeline (#2584) 
Co-authored-by: mishka <gartsocial@gmail.com>
 2023-03-07 13:31:56 -08:00
zxypro
f0b661b8fb [Docs]Fix invalid link to Pokemons dataset (#2583) 2023-03-07 14:26:09 +01:00
Isamu Isozaki
8552fd7efa Added multitoken training for textual inversion. Issue 369 (#661) 
* 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
 2023-03-07 12:09:36 +01:00
Pedro Cuenca
d3ce6f4b1e Support revision in Flax text-to-image training (#2567) 
Support revision in Flax text-to-image training.
 2023-03-07 08:16:31 +01:00
Will Berman
ca7ca11bcd community controlnet inpainting pipelines (#2561) 
* community controlnet inpainting pipelines

* add community member attribution re: @pcuenca
 2023-03-06 12:55:31 -08:00
YiYi Xu
c7da8fd233 add intermediate logging for dreambooth training script (#2557) 
* add  intermediate logging
---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
 2023-03-06 08:13:12 -10:00
Patrick von Platen
b8bfef2ab9 make style 2023-03-06 19:11:45 +01:00
haixinxu
f3f626d556 Allow textual_inversion_flax script to use save_steps and revision flag (#2075) 
* Update textual_inversion_flax.py

* Update textual_inversion_flax.py

* Typo

sorry.

* Format source
 2023-03-06 19:11:27 +01:00
Patrick von Platen
56958e1177 [Training] Fix tensorboard typo (#2566) 2023-03-06 15:13:38 +01:00
Naga Sai Abhinay
2e3541d7f4 [Community Pipeline] Unclip Image Interpolation (#2400) 
* unclip img interpolation poc

* Added code sample and refactoring.
 2023-03-05 16:55:30 -08:00
Alex McKinney
5e5ce13e2f adds xformers support to train_unconditional.py (#2520) 2023-03-03 18:35:59 +01:00
Patrick von Platen
3d2648d743 [Post release] Push post release (#2546) 2023-03-03 18:11:01 +01:00
Patrick von Platen
f20c8f5a1a Release: v0.14.0 2023-03-03 16:45:08 +01:00
Isamu Isozaki
d9b9533c7e Textual inv make save log both steps (#2178) 
* Initial commit

* removed images

* Made logging the same as save

* Removed logging function

* Quality fixes

* Quality fixes

* Tested

* Added support back for validation_epochs

* Fixing styles

* Did changes

* Change to log_validation

* Add extra space after wandb import

* Add extra space after wandb

Co-authored-by: Will Berman <wlbberman@gmail.com>

* Fixed spacing

---------

Co-authored-by: Will Berman <wlbberman@gmail.com>
 2023-03-02 19:04:18 +01:00
Patrick von Platen
eadf0e2555 [Copyright] 2023 (#2524) 2023-03-01 10:31:00 +01:00
Pedro Cuenca
5de4347663 Fix test train_unconditional (#2481) 
* Fix tensorboard tracking with `accelerate` @ `main`

* Fix `train_unconditional.py` with accelerate from main.
 2023-02-24 14:31:16 -08:00
Haofan Wang
589faa8c88 Update train_text_to_image_lora.py (#2464) 
* Update train_text_to_image_lora.py

* Update train_text_to_image_lora.py
 2023-02-23 11:08:21 +05:30
Patrick von Platen
3231712b7d Post release 0.14 2023-02-17 23:57:46 +02:00
Patrick von Platen
b2c1e0d6d4 Release: v0.13.0 2023-02-17 23:38:05 +02:00
Will Berman
bfdffbea32 add xformers 0.0.16 warning message (#2345) 
* add xformers 0.0.16 warning message

* fix version check to check whole version string
 2023-02-17 13:25:46 -08:00
Will Berman
5979089713 Revert "Release: v0.13.0" (#2405) 
This reverts commit 024c4376fb.
 2023-02-17 10:48:16 -08:00
Patrick von Platen
024c4376fb Release: v0.13.0 2023-02-17 18:46:00 +02:00
Patrick von Platen
ca980fd0d1 [Examples] Make sure EMA works with any device (#2382) 
* Fix EMA

* up

* update
 2023-02-16 21:27:47 +01:00
Will Berman
b214bb25f8 train_text_to_image EMAModel saving (#2341) 2023-02-16 14:40:28 +01:00
Damian Stewart
e3ddbe25ed Fix 3-way merging with the checkpoint_merger community pipeline (#2355) 
correctly locate 3rd file; also correct misleading docs
 2023-02-16 10:52:41 +01:00
Will Berman
46def7265f checkpointing_steps_total_limit->checkpoints_total_limit (#2374) 2023-02-16 00:28:58 -08:00
Will Berman
296b01e1a1 add total number checkpoints to training scripts (#2367) 
* 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>
 2023-02-15 23:58:06 -08:00
Patrick von Platen
91925fbb76 Fix callback type hints - no optional function argument (#2357) 
replace type hints
 2023-02-14 14:35:05 -08:00
Ben Evans
0db19da01f Log Unconditional Image Generation Samples to W&B (#2287) 
* 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>
 2023-02-14 23:11:12 +01:00
Will Berman
9e8ee2ace1 dreambooth checkpointing tests and docs (#2339) 2023-02-13 14:16:32 -08:00
Naga Sai Abhinay
a688c7bdfb [Community Pipeline] UnCLIP Text Interpolation Pipeline (#2257) 
* UnCLIP Text Interpolation Pipeline

* Formatter fixes

* Changes based on feedback

* Formatting fix

* Formatting fix

* isort formatting fix(?)

* Remove duplicate code

* Formatting fix

* Refactor __call__ and change example in readme.

* Update examples/community/unclip_text_interpolation.py

Refactor to linter formatting

Co-authored-by: Will Berman <wlbberman@gmail.com>

---------

Co-authored-by: Will Berman <wlbberman@gmail.com>
 2023-02-12 22:16:18 -08:00
Patrick von Platen
e83b43612b make style 2023-02-10 13:07:46 +02:00
erkams
1be7df0205 [LoRA] Freezing the model weights (#2245) 
* [LoRA] Freezing the model weights

Freeze the model weights since we don't need to calculate grads for them.

* Apply suggestions from code review

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

* Apply suggestions from code review

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
 2023-02-09 11:45:11 +01:00
Patrick von Platen
62a15cec6e make style 2023-02-09 12:27:44 +02:00
Ben Evans
f3c848383a Run same number of DDPM steps in inference as training (#2263) 
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.
 2023-02-09 10:36:38 +01:00
Patrick von Platen
1ed6b77781 [Examples] Test all examples on CPU (#2289) 
* [Examples] Test all examples on CPU

* add

* correct

* Apply suggestions from code review
 2023-02-08 15:59:13 +01:00
Chenguo Lin
9d0d070996 EMA: fix state_dict() and load_state_dict() & add cur_decay_value (#2146) 
* EMA: fix `state_dict()` & add `cur_decay_value`

* EMA: fix a bug in `load_state_dict()`

'float' object (`state_dict["power"]`) has no attribute 'get'.

* del train_unconditional_ort.py
 2023-02-08 10:44:50 +01:00
Isamu Isozaki
c1971a53bc Textual inv save log memory (#2184) 
* Quality check and adding tokenizer

* Adapted stable diffusion to mixed precision+finished up style fixes

* Fixed based on patrick's review

* Fixed oom from number of validation images

* Removed unnecessary np.array conversion

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-02-08 10:37:10 +01:00
Patrick von Platen
a7ca03aa85 Replace flake8 with ruff and update black (#2279) 
* before running make style

* remove left overs from flake8

* finish

* make fix-copies

* final fix

* more fixes
 2023-02-07 23:46:23 +01:00
Patrick von Platen
f5ccffecf7 Use accelerate save & loading hooks to have better checkpoint structure (#2048) 
* better accelerated saving

* up

* finish

* finish

* uP

* up

* up

* fix

* Apply suggestions from code review

* correct ema

* Remove @

* up

* Apply suggestions from code review

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

* Update docs/source/en/training/dreambooth.mdx

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

---------

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
 2023-02-07 20:03:59 +01:00
wfng92
111228cb39 Fix torchvision.transforms and transforms function naming clash (#2274) 
* 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>
 2023-02-07 17:36:32 +01:00
wfng92
b1dad2e9d3 Make center crop and random flip as args for unconditional image generation (#2259) 
* 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
 2023-02-07 11:58:31 +01:00
Patrick von Platen
cd52475560 [Examples] Remove datasets important that is not needed (#2267) 
* [Examples] Remove datasets important that is not needed

* remove from lora tambien
 2023-02-07 11:55:34 +01:00
Patrick von Platen
3b66cc0fc1 make style 2023-02-07 08:11:22 +00:00