jiashenggu 80d1150a0e add I2V sft and fix an error (#97) ...

* adaption for CogVideoX1.5

* add patch_size_t in full finetuning of T2V and lora finetuning of I2V

* add I2V sft and add ofs to adapt cogvideox 1.5

2024-12-06 01:59:57 +05:30

..

mochi-1

readme

2024-12-01 20:35:51 +05:30

text_encoder

CogVideoX LoRA and full finetuning (#1)

2024-10-01 08:05:10 +05:30

__init__.py

dataprep.

2024-11-17 08:31:21 +05:30

args.py

docs: fix help message in args.py (#98)

2024-11-27 08:27:41 +05:30

cogvideox_image_to_video_lora.py

add I2V sft and fix an error (#97)

2024-12-06 01:59:57 +05:30

cogvideox_image_to_video_sft.py

add I2V sft and fix an error (#97)

2024-12-06 01:59:57 +05:30

cogvideox_text_to_video_lora.py

RoPE fixes for 1.5, bfloat16 support in prepare_dataset, gradient_accumulation grad norm undefined fix (#107)

2024-12-02 15:12:12 +05:30

cogvideox_text_to_video_sft.py

RoPE fixes for 1.5, bfloat16 support in prepare_dataset, gradient_accumulation grad norm undefined fix (#107)

2024-12-02 15:12:12 +05:30

dataset.py

revert changes to training/dataset.py

2024-11-19 10:29:16 +05:30

prepare_dataset.py

RoPE fixes for 1.5, bfloat16 support in prepare_dataset, gradient_accumulation grad norm undefined fix (#107)

2024-12-02 15:12:12 +05:30

utils.py

RoPE fixes for 1.5, bfloat16 support in prepare_dataset, gradient_accumulation grad norm undefined fix (#107)

2024-12-02 15:12:12 +05:30