storytold/FineTrainers-Conditioning
2
0
Fork 0
mirror of https://github.com/storytold/FineTrainers-Conditioning.git synced 2026-10-17 00:23:35 +00:00
Code Issues Packages Projects Releases Wiki Activity
175 Commits 6 Branches 0 Tags
eb6b0f596a56b3fb324c071768b573cbb6d1164d
Commit Graph

68 Commits

Author SHA1 Message Date
CrossProduct eb6b0f596a There was a results_args mapping that needed to be modified. 2025-01-12 05:09:42 +00:00
CrossProduct 4354fb3164 LTX uses a default frame rate of 24 FPS 
We need to modify the output validation framerate to match that value.
Add Framerate args.
Add Update video output and inference frame rate
 2025-01-12 04:39:05 +00:00
Aryan a78fedd108 Merge branch 'main' into feature/full-finetuning 2025-01-11 07:17:29 +05:30
Aryan a3898075d1 Helpful mesages (#210) 2025-01-11 06:35:28 +05:30
Aryan d3b797ee35 Improve argument handling (#209) 2025-01-11 06:18:13 +05:30
Aryan ca957e543c remove unnecessary changes 2025-01-11 01:37:02 +01:00
Aryan 491b35f3dd Merge branch 'main' into feature/full-finetuning 2025-01-11 05:59:08 +05:30
Aryan 1f304b36d4 handle saving of final model weights correctly 2025-01-11 01:28:47 +01:00
Aryan 06dd96c0a3 remove unnecessary changes 2025-01-11 01:11:27 +01:00
Aryan d6821c3da8 refactor 2025-01-11 00:54:03 +01:00
Aryan 81bf590a91 Argument descriptions (#208) 
* add argument descriptions

* update

* update

* update
 2025-01-11 05:06:02 +05:30
Sayak Paul 014960fd4c Merge branch 'main' into feature/full-finetuning 2025-01-10 19:56:34 +05:30
Boyang Deng b34091362e Fix the checkpoint dir bug in get_intermediate_ckpt_path so that checkpointing_limit can actually work. (#207) 2025-01-10 13:18:32 +05:30
sayakpaul a422f7f07b updates 2025-01-10 07:53:16 +05:30
Sayak Paul 6d597699b3 Merge branch 'main' into feature/full-finetuning 2025-01-10 07:49:06 +05:30
sayakpaul c0f38892f8 remove __class__. 2025-01-10 07:44:36 +05:30
sayakpaul 2c6f5497a5 Merge branch 'main' into auxiliary-support-ff-2 2025-01-09 14:26:32 +05:30
Aryan b9a6492ad1 Epoch loss (#201) 
* update

* update
 2025-01-09 14:22:56 +05:30
sayakpaul 162e6cd50d fix subfolder bug. 2025-01-09 13:25:01 +05:30
sayakpaul 5183405e61 tackle validation. 2025-01-09 13:17:15 +05:30
sayakpaul 8188f8a11e tackle saving and loading hooks. 2025-01-09 13:03:14 +05:30
sayakpaul acffc2d9fc parse subfolder when needed. 2025-01-09 12:54:57 +05:30
Sayak Paul f311f16d98 [core] Fix loading of precomputed conditions and latents (#199) 
* support precomputation.

* fixes
 2025-01-09 12:43:03 +05:30
CrossProduct 19bba0aed3 Run linter. 2025-01-09 00:39:20 +00:00
CrossProduct d0ee9c3101 Switching to Full FineTuning 2025-01-09 00:27:15 +00:00
Sayak Paul 72ec207708 Merge branch 'main' into feature/full-finetuning 2025-01-08 10:49:13 +05:30
Aryan dbffc80e7c Precomputation folder name based on model name (#196) 
* update

* update

* fix

* address review comments
 2025-01-08 08:45:44 +05:30
ArEnSc bd02e6d9d2 Merge branch 'main' into feature/full-finetuning 2025-01-07 19:14:25 -05:00
ArEnSc 905c22edd8 Fix minor bug with function call that doesn't exist. (#195) 
Co-authored-by: Aryan <aryan@huggingface.co>
 2025-01-08 05:25:27 +05:30
CrossProduct cb9381b40e Suggestions Addressed 
Renamed to SFT
Added 2 other models.
Testing required.
 2025-01-07 22:59:09 +00:00
CrossProduct 4cd5a8e53b Used disable grad for component on lora fine tuning enabled 2025-01-07 20:41:12 +00:00
CrossProduct f0db0ccb00 Change name of the flag 2025-01-07 20:36:03 +00:00
CrossProduct eeea82ad04 Full Finetuning for LTX possibily extended to other models. 2025-01-07 20:27:19 +00:00
Aryan 38413aa167 Allow images; Remove LLM generated prefixes; Allow JSON/JSONL; Fix bugs (#158) 
* update

* update

* fix

* Update finetrainers/dataset.py

* update

* argument for enabling remove of common llm prefixes

* update

* make new generator for validation

* update

* update

* update

* update

* update
 2025-01-06 18:52:54 +05:30
Sayak Paul b3d0ba8e12 support model cards (#176) 
* introduce model cards and support passing FPS.

* updates

* fix

* fix

* updates

* revert changes

* revert args.py changes

* fix

* fix

* fix filename
 2025-01-05 19:21:17 +05:30
Sayak Paul a709a1cec1 fixes (#178) 2025-01-04 08:57:41 +05:30
Sayak Paul 071c140879 Fix scheduler bugs (#177) 
* fix scheduler bugs.

* fix
 2025-01-03 18:52:40 +05:30
Sayak Paul b8352abf70 Support CogVideoX T2V (#165) 
* support cog t2v.

* generator.

* updates

* style

* fixes

* fix padding frames.

Co-authored-by: zRzRzRzRzRzRzR <Yuxuan.Zhang2104@student.xjtlu.edu.cn>

* revert changes related to generator.

* refactor a lot of things.

* accept revision and cache_dir.

* remove unused var

* refactoring fixes.

* refactor

* update

* update

---------

Co-authored-by: zRzRzRzRzRzRzR <Yuxuan.Zhang2104@student.xjtlu.edu.cn>
Co-authored-by: Aryan <aryan@huggingface.co>
 2025-01-03 10:53:16 +05:30
Sayak Paul 018953ed86 bulk update styling and formatting (#170) 2025-01-02 13:20:33 +05:30
Sayak Paul 191ea8b0cc [optimization] support 8bit optims from bistandbytes (#163) 
* support 8bit optims from bnb.

* fix exist_ok

* use_8bit_bnb.

* fix.

* note in readme.
 2024-12-30 14:03:56 +05:30
sayakpaul 84c17561eb fixes 2024-12-27 15:02:21 +05:30
sayakpaul 4461cdd98f tracker logging 2024-12-27 12:25:11 +05:30
Aryan a19401e84f update README; remove print; make style 2024-12-27 07:19:16 +01:00
sayakpaul 87af1a0113 Merge branch 'main' into support-deepspeed 2024-12-26 08:17:48 +05:30
sayakpaul 1d5e0566fb private 2024-12-26 08:01:16 +05:30
Sayak Paul 0309f3bf67 Apply suggestions from code review 
Co-authored-by: Aryan <aryan@huggingface.co>
 2024-12-26 08:00:04 +05:30
sayakpaul 0c0a0a5e4a scheduler 2024-12-26 07:55:07 +05:30
sayakpaul 28ecfe6b65 torch.is_tensor check 2024-12-26 07:49:51 +05:30
Aryan 2a594ea2db fix validation bug (#149) 2024-12-26 02:54:08 +05:30
Aryan 5757b1b886 fix grad norm related logging 2024-12-25 19:25:22 +01:00