mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-18 22:08:13 +00:00
b272253956
* add 2.3 i2v training scripts * add frame resampling by fixed fps * LoadVideo: add compatibility for not fix_frame_rate * refactor frame resampler * minor fix
40 lines
1.6 KiB
Bash
40 lines
1.6 KiB
Bash
# Splited Training
|
|
accelerate launch examples/ltx2/model_training/train.py \
|
|
--dataset_base_path data/example_video_dataset/ltx2 \
|
|
--dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
|
|
--data_file_keys "video,input_audio" \
|
|
--extra_inputs "input_audio,input_image" \
|
|
--height 512 \
|
|
--width 768 \
|
|
--num_frames 121 \
|
|
--dataset_repeat 1 \
|
|
--model_id_with_origin_paths "DiffSynth-Studio/LTX-2.3-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2.3-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2.3-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" \
|
|
--learning_rate 1e-4 \
|
|
--num_epochs 5 \
|
|
--remove_prefix_in_ckpt "pipe.dit." \
|
|
--output_path "./models/train/LTX2.3-I2AV_lora-splited-cache" \
|
|
--lora_base_model "dit" \
|
|
--lora_target_modules "to_k,to_q,to_v,to_out.0" \
|
|
--lora_rank 32 \
|
|
--use_gradient_checkpointing \
|
|
--task "sft:data_process"
|
|
|
|
accelerate launch examples/ltx2/model_training/train.py \
|
|
--dataset_base_path ./models/train/LTX2.3-I2AV_lora-splited-cache \
|
|
--data_file_keys "video,input_audio" \
|
|
--extra_inputs "input_audio,input_image" \
|
|
--height 512 \
|
|
--width 768 \
|
|
--num_frames 121 \
|
|
--dataset_repeat 100 \
|
|
--model_id_with_origin_paths "DiffSynth-Studio/LTX-2.3-Repackage:transformer.safetensors" \
|
|
--learning_rate 1e-4 \
|
|
--num_epochs 5 \
|
|
--remove_prefix_in_ckpt "pipe.dit." \
|
|
--output_path "./models/train/LTX2.3-I2AV_lora" \
|
|
--lora_base_model "dit" \
|
|
--lora_target_modules "to_k,to_q,to_v,to_out.0" \
|
|
--lora_rank 32 \
|
|
--use_gradient_checkpointing \
|
|
--task "sft:train"
|