7 Commits

Author	SHA1	Message	Date
Yuxuan Zhang	39c6562dc8	format	2025-03-22 15:14:06 +08:00
zR	1534bf33eb	add pipeline	2025-01-12 19:27:21 +08:00
OleehyO	36427274d6	style: format import statements across finetune module	2025-01-07 05:54:52 +00:00
zR	1789f07256	format and check fp16 for cogvideox2b	2025-01-07 13:16:18 +08:00
OleehyO	66e4ba2592	fix(cogvideox): add prompt embedding caching and fix frame padding ... - Add support for cached prompt embeddings in dataset - Fix bug where first frame wasn't properly padded in latent space	2025-01-04 06:16:42 +00:00
OleehyO	a001842834	feat: implement CogVideoX trainers for I2V and T2V tasks ... Add and refactor trainers for CogVideoX model variants: - Implement CogVideoXT2VLoraTrainer for text-to-video generation - Refactor CogVideoXI2VLoraTrainer for image-to-video generation Both trainers support LoRA fine-tuning with proper handling of: - Model components loading and initialization - Video encoding and batch collation - Loss computation with noise prediction - Validation step for generation	2025-01-01 15:10:54 +00:00
OleehyO	85e00a1082	feat(models): add scaffolding	2025-01-01 15:10:40 +00:00