Commit Graph

Select branches

Hide Pull Requests

CogVideo

CogVideoX_dev

main

#101

#104

#107

#110

#119

#120

#121

#124

#129

#132

#133

#14

#142

#143

#150

#151

#155

#157

#16

#163

#165

#169

#173

#178

#179

#181

#183

#188

#195

#196

#206

#208

#210

#216

#224

#253

#254

#258

#259

#261

#268

#271

#272

#275

#280

#285

#286

#287

#288

#29

#290

#295

#297

#299

#303

#304

#317

#318

#328

#329

#334

#335

#336

#358

#362

#364

#365

#376

#379

#38

#380

#382

#383

#389

#400

#402

#411

#416

#417

#418

#419

#432

#434

#460

#462

#465

#468

#469

#470

#474

#500

#507

#515

#52

#537

#538

#544

#556

#565

#567

#58

#581

#585

#599

#603

#607

#615

#62

#632

#642

#65

#651

#652

#654

#656

#657

#67

#678

#682

#709

#71

#716

#719

#722

#726

#729

#730

#739

#74

#743

#76

#77

#79

#80

#82

#90

#94

#95

v1.0

Mono Color

• 5ab1e2449f
  Merge pull request #719 from holma91/fix-lora-scale main OleehyO 2025-03-25 18:59:49 +08:00
• a01ffd9aba
  Update cli_demo.py OleehyO 2025-03-25 18:59:11 +08:00
• 9be282d461
  Merge branch 'main' into fix-lora-scale OleehyO 2025-03-25 18:58:33 +08:00
• c624cb0d91
  Merge pull request #743 from THUDM/CogVideoX_dev Yuxuan Zhang 2025-03-24 11:30:17 +08:00
• 39c6562dc8 format CogVideoX_dev Yuxuan Zhang 2025-03-22 15:14:06 +08:00
• b9b0539dbe update Yuxuan Zhang 2025-03-15 14:27:12 +08:00
• 129c375c85
  Merge pull request #729 from zhuhz22/riflex Yuxuan Zhang 2025-03-03 10:57:29 +08:00
• 536b705105
  Merge pull request #730 from THUDM/CogVideoX_dev Yuxuan Zhang 2025-03-03 10:56:19 +08:00
• a691a6dd35 Update wechat.jpg Yuxuan Zhang 2025-03-03 10:52:22 +08:00
• 6454293a1d add friendly link of RIFLEx zhuhz22 2025-03-01 22:06:39 +08:00
• 887a4c7365
  Merge pull request #726 from THUDM/CogVideoX_dev Yuxuan Zhang 2025-03-01 09:29:09 +08:00
• a494fa50cd Merge branch 'CogVideoX_dev' of https://github.com/THUDM/CogVideo into CogVideoX_dev Yuxuan Zhang 2025-02-27 17:33:23 +08:00
• 4fb6766d7c fix import decord error Yuxuan Zhang 2025-02-27 17:33:20 +08:00
• 8d90381ba8
  Merge pull request #722 from THUDM/main Yuxuan Zhang 2025-02-27 17:32:24 +08:00
• eb66c9c6dc
  Merge pull request #709 from LittleNyima/feature/ddim-inversion Yuxuan Zhang 2025-02-27 13:24:24 +08:00
• 2c33c0982b fix import order and deprecate for CVX 2B models LittleNyima 2025-02-26 15:54:58 +08:00
• d6bb910697
  Merge branch 'THUDM:main' into feature/ddim-inversion LittleNyima 2025-02-26 15:22:08 +08:00
• 84766d02e8 fix scale bug holma91 2025-02-24 20:08:27 +01:00
• e0bf395458
  make the style of argparser consistent with repo LittleNyima 2025-02-23 19:41:21 +08:00
• e44c9f2c83
  Merge pull request #716 from THUDM/CogVideoX_dev Yuxuan Zhang 2025-02-22 17:09:50 +08:00
• 5be6c0512f Merge remote-tracking branch 'upstream/CogVideoX_dev' into dev OleehyO 2025-02-22 06:06:03 +00:00
• 4dac252c63 [chore] Update gitignore patterns and project dependencies OleehyO 2025-02-22 06:03:53 +00:00
• 250a0bce45 stable version LittleNyima 2025-02-20 05:03:15 +00:00
• 58d66c8a08
  Implement an unverified version that should be further tested LittleNyima 2025-02-20 01:39:12 +08:00
• dd76b2b9ea Initialize DDIM Inversion script LittleNyima 2025-02-18 09:50:55 +00:00
• 34c6ba22ab
  Merge pull request #682 from THUDM/main Yuxuan Zhang 2025-01-22 09:49:34 +08:00
• bbe909d7f7
  Merge pull request #678 from THUDM/CogVideoX_dev Yuxuan Zhang 2025-01-22 09:47:24 +08:00
• ea994c75c2
  Merge pull request #652 from erfanasgari21/moviepy-v2 Yuxuan Zhang 2025-01-21 22:29:15 +08:00
• aa12ed37f5
  Merge branch 'main' into moviepy-v2 Yuxuan Zhang 2025-01-20 21:46:07 +08:00
• d9e2a415e8 fix: fix resolution handling for different model types OleehyO 2025-01-20 09:48:17 +00:00
• 0e26f54cbe docs: clarify frame number requirements for CogVideoX models OleehyO 2025-01-20 09:43:45 +00:00
• c1ca70ba67
  Merge pull request #654 from THUDM/CogVideoX_dev Yuxuan Zhang 2025-01-20 11:15:50 +08:00
• bf73742c05 docs: enhance CLI demo documentation OleehyO 2025-01-16 09:34:52 +00:00
• bf9c351a10 deps: upgrade diffusers to >=0.32.1 OleehyO 2025-01-16 09:08:44 +00:00
• 0e78f20629 Merge remote-tracking branch 'upstream/CogVideoX_dev' into dev OleehyO 2025-01-14 04:00:11 +00:00
• 4615479b51 move to tools Yuxuan Zhang 2025-01-14 11:33:02 +08:00
• 7993670957 zero_to_bf16 Yuxuan Zhang 2025-01-14 11:31:25 +08:00
• 4878edd0cf fix: correct do_validation argument parsing OleehyO 2025-01-13 12:48:21 +00:00
• 78275b0480 add comment of bash scripts Yuxuan Zhang 2025-01-13 20:02:06 +08:00
• 455b44a7b5 chore: code cleanup and parameter optimization OleehyO 2025-01-13 11:53:13 +00:00
• 954ba28d3c Merge remote-tracking branch 'upstream/CogVideoX_dev' into dev OleehyO 2025-01-13 11:48:24 +00:00
• 4f1cc66815 fix: correct LoRA loading and resolution dimensions OleehyO 2025-01-13 10:49:46 +00:00
• 1534bf33eb add pipeline zR 2025-01-12 19:27:21 +08:00
• 86a0226f80 Merge remote-tracking branch 'upstream/CogVideoX_dev' into dev OleehyO 2025-01-12 08:52:07 +00:00
• 70c899f444 chore: update default training configurations OleehyO 2025-01-12 08:50:15 +00:00
• b362663679 fix: normalize image tensors in I2VDataset OleehyO 2025-01-12 06:01:48 +00:00
• 30ba1085ff Merge remote-tracking branch 'upstream/main' into dev OleehyO 2025-01-12 05:58:07 +00:00
• 3252614569 Add pydantic dependency OleehyO 2025-01-12 05:56:24 +00:00
• f66f1647e2
  Merge pull request #657 from ZGCTroy/main OleehyO 2025-01-12 13:55:12 +08:00
• f5169385bd docs: add SFT support documentation in multilingual README OleehyO 2025-01-12 05:37:50 +00:00
• 795dd144a4 Rename lora training scripts as ddp OleehyO 2025-01-12 05:36:32 +00:00
• fdb9820949 feat: support DeepSpeed ZeRO-3 and optimize peak memory usage OleehyO 2025-01-12 05:33:56 +00:00
• 09a49d3546
  fix bug of i2v; video is already 0-255 Zheng Guang Cong 2025-01-11 17:29:27 +08:00
• cd861bbe1e
  Update i2v_dataset.py Zheng Guang Cong 2025-01-11 17:24:35 +08:00
• 35383e2db3
  fix potential bug of i2v Zheng Guang Cong 2025-01-11 17:08:25 +08:00
• 7dc8516bcb add comment as #653 zR 2025-01-11 12:53:32 +08:00
• 2f275e82b5 Merge remote-tracking branch 'upstream/CogVideoX_dev' into dev OleehyO 2025-01-11 02:16:09 +00:00
• caa24bdc36 feat: add SFT support with ZeRO optimization strategies OleehyO 2025-01-11 02:13:32 +00:00
• e213b6c083 fix: pad latent frames to match patch_size_t requirements OleehyO 2025-01-11 02:08:07 +00:00
• 70ca65300c
  upgrade to moviepy v2 Erfan Asgari 2025-01-11 00:18:24 +03:30
• 6f43c5ef65
  Pin moviepy to v1.0.3 to avoid breaking changes in v2 Erfan Asgari 2025-01-10 20:25:01 +03:30
• 6a78278c0b
  Update README.md Erfan Asgari 2025-01-10 20:22:25 +03:30
• f6d722cec7 fix: remove copying first video frame as conditioning image OleehyO 2025-01-09 15:52:51 +00:00
• 07766001f6 feat(dataset): pad short videos by repeating last frame OleehyO 2025-01-08 02:14:56 +00:00
• 8f1829f1cd
  Merge pull request #642 from THUDM/CogVideoX_dev Yuxuan Zhang 2025-01-08 09:51:39 +08:00
• 045e1b308b readme zR 2025-01-08 09:50:08 +08:00
• 249fadfb76 docs: add hardware requirements for model training OleehyO 2025-01-08 01:39:37 +00:00
• 10de04fc08 perf: cast VAE and text encoder to target dtype before precomputing cache OleehyO 2025-01-08 01:38:13 +00:00
• 0e21d41b12 Merge remote-tracking branch 'upstream/CogVideoX_dev' into dev OleehyO 2025-01-07 09:51:48 +00:00
• 392e37021a Add video path to error message for better debugging OleehyO 2025-01-07 09:50:21 +00:00
• 11935892ae remove --image_column zR 2025-01-07 16:37:11 +08:00
• ee1f666206 docs: update READMEs with auto first-frame extraction feature OleehyO 2025-01-07 06:45:10 +00:00
• e084a4a270 feat: auto-extract first frames as conditioning images for i2v model OleehyO 2025-01-07 06:43:26 +00:00
• 96e511b413 feat: add warning for fp16 mixed precision training OleehyO 2025-01-07 06:00:38 +00:00
• 36427274d6 style: format import statements across finetune module OleehyO 2025-01-07 05:47:39 +00:00
• 1789f07256 format and check fp16 for cogvideox2b zR 2025-01-07 13:16:18 +08:00
• 1b886326b2 Merge remote-tracking branch 'upstream/CogVideoX_dev' into dev OleehyO 2025-01-06 10:47:56 +00:00
• 9157e0cbc8 Adapt dataset for text embeddings and add noise padding OleehyO 2025-01-06 10:44:58 +00:00
• 49dc370de6 fix: remove pipeline hooks after validation OleehyO 2025-01-04 06:21:17 +00:00
• 93b906b3fb docs: clarify train_frames includes padding frame OleehyO 2025-01-04 06:20:25 +00:00
• 7e1ac76847 feat(cogvideox): add prompt embedding caching support OleehyO 2025-01-04 06:17:56 +00:00
• 66e4ba2592 fix(cogvideox): add prompt embedding caching and fix frame padding OleehyO 2025-01-03 09:27:33 +00:00
• de5bef6611 feat(args): add train_resolution validation for video frames and resolution OleehyO 2025-01-03 08:48:42 +00:00
• ffb6ee36b4 docs: update finetune documentation in all languages OleehyO 2025-01-03 08:30:41 +00:00
• c817e7f062 chore: update default training parameters for t2v and i2v scripts OleehyO 2025-01-03 08:27:49 +00:00
• e5b8f9a2ee feat: add caching for prompt embeddings OleehyO 2025-01-03 07:52:10 +00:00
• f731c35f70 Add unload_model function OleehyO 2025-01-03 07:50:36 +00:00
• ce2c299c1f Update diffusion_video.py zR 2025-01-03 08:45:42 +08:00
• b080c6a010 put lora back(sat), unavailable running zR 2025-01-02 11:48:18 +08:00
• a88c1ede69 feat(args): add validation for training resolution OleehyO 2025-01-02 03:12:09 +00:00
• 362b7bf273 docs: update README in multiple languages OleehyO 2025-01-02 03:07:34 +00:00
• aa240dc675
  Merge pull request #632 from THUDM/CogVideoX_dev Yuxuan Zhang 2025-01-02 08:31:25 +08:00
• cf2fff7e55 Merge remote-tracking branch 'upstream/main' into dev OleehyO 2025-01-01 16:03:51 +00:00
• 7fa1bb48be refactor: remove deprecated training scripts OleehyO 2025-01-01 15:56:14 +00:00
• 48ad178818 Reorganize training script arguments OleehyO 2025-01-01 15:52:39 +00:00
• 6ef15dd2a5 docs: update TOC and add friendly link in README files 三洋三洋 2024-12-27 19:37:08 +08:00
• 6e79472417 feat: add training launch scripts for I2V and T2V models OleehyO 2025-01-01 14:53:45 +00:00
• 26b87cd4ff feat(args): add validation and arg interface for training parameters OleehyO 2025-01-01 14:40:09 +00:00
• 04a60e7435 Change logger name to trainer OleehyO 2025-01-01 14:22:59 +00:00
• a001842834 feat: implement CogVideoX trainers for I2V and T2V tasks OleehyO 2024-12-31 17:27:47 +00:00