Commit graph

Select branches

Hide pull requests

Laurent2916-patch-installation-instructions

add_more_readme_badges

add_multiupscale_test_small_image

gh-pages

main

make_hub_expected_hash_optional

pr/FG-2941-implement-ic-light

pr/add-docstrings

pr/add_comfyui_custom_nodes

pr/check_refiners_conversion_deps

pr/comfy-readme-nits

pr/comfyui_nodes_add_requirements_txt_files

pr/comfyui_nodes_fix_requirements_txt_file

pr/comfyui_refiners_1.0.4

pr/fix_broken_ci_docs_deployements

pr/fix_broken_dpm_solver_test

pr/fix_broken_gaussian_blur_test

pr/fix_broken_test_from_pytorch_update

pr/fix_sd_unet_device_dtype_and_also_export

pr/fix_test_ic_light

pr/gh-custom-domain

pr/gradute_multiupscaler

pr/hq-sam-test-predictor-equal

pr/hq-sam-weights

pr/latent-diffusion-solver-assert-step-msg

pr/loosen_some_failing_sam_tests

pr/move_some_tests_into_adapters_folder

pr/purge_some_from_torch_imports

pr/sam-mask-decoder-arg

pr/sam-multimask-output

pr/skip-lock-files

pr/update_latest_news_multi_upsacler

pr/use_torch.optim.optimizer.ParamsT

remove_useless_overloads_image_prompt

scm_package_versionning

#1

#10

#100

#101

#102

#103

#104

#105

#106

#107

#108

#109

#11

#110

#111

#112

#113

#114

#115

#117

#118

#119

#12

#120

#121

#122

#123

#124

#125

#126

#127

#128

#129

#13

#130

#131

#132

#133

#134

#136

#137

#138

#139

#14

#140

#141

#142

#143

#144

#145

#146

#147

#148

#149

#15

#150

#151

#152

#153

#154

#155

#156

#157

#158

#159

#16

#160

#161

#162

#163

#164

#165

#166

#167

#168

#169

#17

#170

#171

#172

#173

#174

#175

#176

#177

#178

#179

#18

#180

#181

#182

#183

#184

#185

#188

#189

#19

#190

#191

#192

#193

#194

#195

#196

#197

#198

#199

#2

#20

#200

#201

#202

#203

#204

#205

#206

#207

#208

#209

#21

#210

#211

#212

#213

#214

#215

#216

#217

#218

#219

#22

#220

#221

#222

#223

#224

#225

#227

#228

#229

#23

#230

#231

#232

#233

#234

#235

#236

#238

#239

#24

#240

#241

#242

#243

#244

#245

#246

#247

#248

#249

#25

#250

#251

#252

#253

#254

#256

#257

#258

#259

#26

#260

#261

#262

#263

#264

#265

#266

#267

#268

#269

#27

#270

#271

#272

#273

#274

#275

#276

#277

#278

#278

#279

#28

#280

#281

#282

#283

#284

#285

#286

#287

#288

#289

#29

#290

#290

#291

#292

#293

#294

#295

#296

#297

#298

#299

#3

#30

#300

#301

#302

#303

#304

#305

#306

#307

#308

#309

#31

#310

#311

#312

#313

#314

#315

#316

#317

#318

#319

#32

#320

#321

#322

#323

#324

#325

#326

#327

#328

#329

#33

#330

#331

#332

#333

#334

#335

#336

#337

#338

#339

#34

#340

#341

#342

#343

#344

#345

#346

#347

#348

#349

#35

#350

#351

#352

#353

#354

#355

#356

#357

#358

#359

#36

#360

#361

#362

#363

#364

#365

#366

#367

#368

#369

#37

#371

#372

#373

#375

#376

#378

#379

#38

#380

#381

#382

#383

#384

#385

#386

#387

#388

#389

#39

#390

#391

#392

#394

#397

#398

#4

#40

#400

#401

#402

#403

#407

#408

#409

#41

#410

#411

#412

#413

#414

#415

#416

#417

#419

#42

#420

#421

#422

#423

#424

#425

#426

#427

#428

#429

#43

#431

#432

#433

#438

#439

#44

#440

#441

#442

#443

#444

#446

#448

#449

#45

#450

#451

#452

#453

#454

#455

#457

#458

#46

#460

#462

#463

#465

#466

#467

#468

#469

#47

#470

#470

#471

#473

#474

#48

#49

#50

#51

#52

#53

#54

#55

#56

#57

#58

#59

#6

#60

#61

#62

#63

#64

#65

#66

#67

#68

#69

#7

#70

#71

#72

#73

#74

#75

#76

#77

#78

#79

#8

#80

#81

#82

#83

#84

#85

#86

#87

#88

#89

#9

#90

#91

#92

#93

#94

#95

#96

#97

#98

#99

v0.1.0

v0.2.0

v0.3.0

v0.3.1

v0.4.0

Mono Color

• 7b52d202f8 fix: palette-image metrics #165 Pierre Colle 2024-01-19 11:16:49 +0100
• 30f4ec2e46 fix: add image-palette evaluation #165 Pierre Colle 2024-01-19 10:43:38 +0100
• aa9f572611 training dependencies are test dependencies Pierre Chapuis 2024-01-19 09:52:38 +0100
• ecf55c4b09 training dependencies are test dependencies Pierre Chapuis 2024-01-19 09:52:38 +0100
• d3f6f4c87d fix: evaluating db samples + zero init adapter + fix eos Pierre Colle 2024-01-19 09:42:09 +0100
• 1bab94ff9d fix: dpm_solver shouldn't be required to "start" on step 0 Bryce 2024-01-18 18:54:26 -0800
• ce3035923b improve DPM solver test Pierre Chapuis 2024-01-18 14:30:13 +0100
• 999e429697 fix bug in dpm_solver_first_order_update Pierre Chapuis 2024-01-18 14:27:30 +0100
• 59db1f0bd5 style Pierre Chapuis 2024-01-18 14:26:39 +0100
• aaddead17d DPM: add a mode to use first order for last step Pierre Chapuis 2024-01-18 11:47:04 +0100
• 1f019cfc08 improve DPM solver test Pierre Chapuis 2024-01-18 14:30:13 +0100
• b8f810dd9b fix bug in dpm_solver_first_order_update Pierre Chapuis 2024-01-18 14:27:30 +0100
• 0470461901 style Pierre Chapuis 2024-01-18 14:26:39 +0100
• 4e9d9371da DPM: add a mode to use first order for last step Pierre Chapuis 2024-01-18 11:47:04 +0100
• 17d9701dde Remove additional noise in final sample of DDIM inference process hugojarkoff 2024-01-18 18:31:00 +0100
• 615baa6000 Remove additional noise in final sample of DDIM inference process hugojarkoff 2024-01-18 18:31:00 +0100
• a1f50f3f9d refactor Lora LoraAdapter and the latent_diffusion/lora file limiteinductive 2024-01-18 15:34:29 +0100
• def2c60ba7 refactor Lora LoraAdapter and the latent_diffusion/lora file limiteinductive 2024-01-18 15:34:29 +0100
• 0cce02b73b lint Pierre Colle 2024-01-18 15:59:24 +0100
• 97fa58b9d0 fix: training color_palette Pierre Colle 2024-01-18 15:56:33 +0100
• dd87b9706e pick the right class for CLIP text converter Cédric Deltheil 2024-01-17 17:15:46 +0100
• 22d8e6b2e9 pick the right class for CLIP text converter Cédric Deltheil 2024-01-17 17:15:46 +0100
• a6a9c8b972 Fix Value dimension in ImageCrossAttention hugojarkoff 2024-01-17 15:53:50 +0100
• ed0b2bfc8f palette adapter Pierre Colle 2024-01-17 16:30:42 +0100
• 0b0581369c Fix Value dimension in ImageCrossAttention hugojarkoff 2024-01-17 15:53:50 +0100
• 483b31bb9b fix: ruff Pierre Colle 2024-01-17 14:33:22 +0100
• a01d1a9205 fix: pyright Pierre Colle 2024-01-17 14:32:16 +0100
• 64deba34b0 fix: create a specific file Pierre Colle 2024-01-17 12:22:51 +0100
• 78ac8f34ed more generic LatentDiffusion Trainer Pierre Colle 2024-01-17 11:59:15 +0100
• 39e5b76e91 pyright linting first tests Pierre Colle 2024-01-17 11:06:20 +0100
• 7839c54ae8 unet conversion: add option to skip init check Pierre Chapuis 2024-01-16 18:40:43 +0100
• d2f38871fd add a way to specify the subfolder of the unet Pierre Chapuis 2024-01-16 15:16:33 +0100
• 94a918a474 fix invalid default value for --half in help Pierre Chapuis 2024-01-16 15:15:52 +0100
• 37381d162b unet conversion: add option to skip init check Pierre Chapuis 2024-01-16 18:40:43 +0100
• e1cc958a22 add a way to specify the subfolder of the unet Pierre Chapuis 2024-01-16 15:16:33 +0100
• 1009137584 fix invalid default value for --half in help Pierre Chapuis 2024-01-16 15:15:52 +0100
• 2b977bc69e fix broken self-attention guidance with ip-adapter limiteinductive 2024-01-16 16:13:40 +0100
• f8c09a7e8f fix broken self-attention guidance with ip-adapter limiteinductive 2024-01-16 16:13:40 +0100
• dca7bc73bf Merge branch 'handle-url-hf-datasets' into color-palette-adapter Pierre Colle 2024-01-16 15:40:21 +0100
• 9c10f98c2e Merge branch 'simple-sharding-manager' into color-palette-adapter Pierre Colle 2024-01-16 15:39:59 +0100
• c593caeb0f move test to test_diffusion.py file Gabriel Vidal-Ayrinhac 2024-01-16 14:46:05 +0100
• febba9d71b minor fix for summarize func Gabriel Vidal-Ayrinhac 2024-01-16 14:44:11 +0100
• d9ae7ca6a5 cast to float32 before converting to image in tensor_to_image to fix bfloat16 conversion limiteinductive 2024-01-15 15:50:40 +0100
• fcb433dd17 cast to float32 before converting to image in tensor_to_image to fix bfloat16 conversion limiteinductive 2024-01-15 15:50:40 +0100
• 2d6476fc64 fix: sharding_manager Pierre Colle 2024-01-16 01:36:34 +0100
• 12cc6af673 Merge branch 'main' of https://github.com/finegrain-ai/refiners into simple-sharding-manager Pierre Colle 2024-01-16 00:54:23 +0100
• fcaae8a87d Merge branch 'main' of https://github.com/finegrain-ai/refiners into handle-url-hf-datasets Pierre Colle 2024-01-16 00:53:55 +0100
• daf3acce16 support image.mode == P Pierre Colle 2024-01-16 00:53:31 +0100
• 14fa0963e2 rollback second_device in conftest Pierre Colle 2024-01-16 00:25:19 +0100
• c063e96ade lint Pierre Colle 2024-01-15 23:58:29 +0100
• a05aaee773 feat: P mode in image Pierre Colle 2024-01-15 23:02:50 +0100
• 0c73c93535 lint Pierre Colle 2024-01-15 23:02:33 +0100
• 138bb08a18 training is running Pierre Colle 2024-01-15 19:49:18 +0100
• 6e5dfa439d rename wrap Pierre Colle 2024-01-15 19:02:58 +0100
• d4256bd7cb clean up hook mechanism Pierre Colle 2024-01-15 18:51:20 +0100
• d999fd4048 clean Pierre Colle 2024-01-15 17:27:29 +0100
• 017099c9ce hook scheduler Pierre Colle 2024-01-15 17:22:04 +0100
• d203974af2 experiments with model device sharding Pierre Colle 2024-01-15 14:41:38 +0100
• fe619658cf feat: add attention emphasis clip adapter Gabriel Vidal-Ayrinhac 2024-01-10 21:49:35 +0100
• 9ab6852463
  Merge branch 'main' into scale_crafter Isamu Isozaki 2024-01-14 22:27:34 -0500
• fcc96fc708 Fix inflate bug isamu-isozaki 2024-01-14 17:58:50 -0500
• c3ea9acbb7 Fixed bug where all conv are replaced isamu-isozaki 2024-01-14 17:43:52 -0500
• 313737b5ca More logging isamu-isozaki 2024-01-14 17:31:17 -0500
• e740e7fe9b Logging isamu-isozaki 2024-01-14 17:22:03 -0500
• 7f722029be add basic unit test for training_utils limiteinductive 2024-01-14 15:06:48 +0100
• 8e2abd4a50 Merge branch 'main' of https://github.com/finegrain-ai/refiners into scale_crafter isamu-isozaki 2024-01-14 16:06:57 -0500
• 33dd31aa6e Added comment isamu-isozaki 2024-01-14 15:53:51 -0500
• 6df196588f Merge branch 'ip_adapter' of https://github.com/isamu-isozaki/refiners into ip_adapter isamu-isozaki 2024-01-14 13:36:23 -0500
• bfd5952398 Made simpler changes isamu-isozaki 2024-01-14 13:34:49 -0500
• a5650b1f3c Merge branch 'main' of https://github.com/finegrain-ai/refiners into ip_adapter isamu-isozaki 2024-01-14 11:58:01 -0500
• 8dd06f27f1 add basic unit test for training_utils limiteinductive 2024-01-14 15:06:48 +0100
• dba9065229
  fix test_debug_print Colle 2024-01-12 18:32:22 +0100
• 42e4e142b9 fix: ruff format Pierre Colle 2024-01-12 18:00:32 +0100
• 46ddaa44a6 Merge branch 'handle-url-hf-datasets' into fabric Pierre Colle 2024-01-12 17:58:23 +0100
• 55624a2097 fix: pyright Pierre Colle 2024-01-12 17:56:18 +0100
• cceb4437ad Merge branch 'module-log-dtype-device' of github.com:piercus/refiners into module-log-dtype-device Pierre Colle 2024-01-12 16:18:10 +0100
• 6058030197 fix: unit test update for #173 Pierre Colle 2024-01-12 16:17:33 +0100
• d9b124230b url dataset Pierre Colle 2024-01-12 16:00:07 +0100
• 636b44281a fabric Pierre Colle 2024-01-12 15:47:59 +0100
• fcba84569d
  
  fix/typo: set adapter's device to trainer's device Laureηt 2024-01-12 14:25:44 +0100
• e45fdd9e57
  
  move the palette embedding computation inside the transform method Laureηt 2024-01-12 14:14:35 +0100
• 8f5ea5ad5d
  
  modify compute_loss and compute_evaluation to use new methods Laureηt 2024-01-12 12:09:13 +0100
• 38a45ee258
  
  (WIP) remove max_color, now uneeded Laureηt 2024-01-12 11:11:47 +0100
• 457c3f5cbd
  display weighted module dtype and device (#173) Colle 2024-01-11 22:37:35 +0100
• 525a59ec70
  
  (WIP) rework heavily ColorEncoder Laureηt 2024-01-11 21:14:57 +0100
• cfea67c812 Update src/refiners/fluxion/layers/module.py Colle 2024-01-11 18:09:19 +0100
• 2d652d1e3f WeightedModule _repr_ change for #173 Pierre Colle 2024-01-11 12:27:29 +0100
• c56be279d1 display module dtype and device Pierre Colle 2024-01-11 08:10:49 +0100
• 14ce2f50f9 make trainer an abstract class limiteinductive 2024-01-11 17:45:40 +0100
• 8862b41f6b make trainer an abstract class limiteinductive 2024-01-11 17:45:40 +0100
• eafbc8a99a prepare_test_weights: refresh IP-Adapter hashes Cédric Deltheil 2024-01-11 14:29:17 +0100
• deed703617 simplify even more CrossAttentionAdapter limiteinductive 2024-01-11 10:29:21 +0100
• 29527c6bcb prepare_test_weights: refresh IP-Adapter hashes Cédric Deltheil 2024-01-11 14:29:17 +0100
• 2abd18518b
  
  add compute_evaluation method to the Trainer Laureηt 2024-01-11 14:17:07 +0100
• 279cbba3d3 simplify even more CrossAttentionAdapter limiteinductive 2024-01-11 10:29:21 +0100
• 3ab8ed2989 remove unused script field from training BaseConfig limiteinductive 2024-01-11 10:53:39 +0100
• 6289388e51 remove unused script field from training BaseConfig limiteinductive 2024-01-11 10:53:39 +0100
• d7cce87fa4 set CUSTOM_DOMAIN in docs.yml GH workflow Cédric Deltheil 2024-01-11 10:57:53 +0100
• eb6c8246b2 set CUSTOM_DOMAIN in docs.yml GH workflow Cédric Deltheil 2024-01-11 10:57:53 +0100
• 91480088fa change favicon to svg format and add logo to config limiteinductive 2024-01-11 10:38:37 +0100