theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

add example_dataset in training scripts (#1358)

Browse Source 
* add example_dataset in training scripts

* fix example datasets
This commit is contained in:
Zhongjie Duan
2026-03-18 15:37:03 +08:00
committed by GitHub
parent 4ec4d9c20a
commit ba0626e38f
196 changed files with 911 additions and 567 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2-T2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
# 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 \
--dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited \
--dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited/metadata.csv \
--data_file_keys "video,input_audio" \
--extra_inputs "input_audio" \
--height 512 \

6
examples/ltx2/model_training/full/LTX-2.3-I2AV-splited.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.3-I2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
# 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 \
--dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.3-I2AV-splited \
--dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.3-I2AV-splited/metadata.csv \
--data_file_keys "video,input_audio" \
--extra_inputs "input_audio,input_image" \
--height 512 \

6
examples/ltx2/model_training/full/LTX-2.3-T2AV-splited.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.3-T2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
# 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 \
--dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-splited \
--dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-splited/metadata.csv \
--data_file_keys "video,input_audio" \
--extra_inputs "input_audio" \
--height 512 \

6
examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2-T2AV-IC-LoRA-splited/*" --local_dir ./data/diffsynth_example_dataset
# 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_iclora.json \
--dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-IC-LoRA-splited \
--dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-IC-LoRA-splited/metadata.json \
--data_file_keys "video,input_audio,in_context_videos" \
--extra_inputs "input_audio,in_context_videos,in_context_downsample_factor,frame_rate" \
--height 512 \

10
examples/ltx2/model_training/lora/LTX-2-T2AV-noaudio.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2-T2AV-noaudio/*" --local_dir ./data/diffsynth_example_dataset
# single stage 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_t2v.csv \
# --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-noaudio \
# --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-noaudio/metadata.csv \
# --height 256 \
# --width 384 \
# --num_frames 25\
@@ -20,8 +22,8 @@
# 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 \
--dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-noaudio \
--dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-noaudio/metadata.csv \
--height 512 \
--width 768 \
--num_frames 121\

10
examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2-T2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
# Single Stage Training not recommended for T2AV due to the large memory consumption. Please use the Splited Training instead.
# 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 \
# --dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited \
# --dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited/metadata.csv \
# --data_file_keys "video,input_audio" \
# --extra_inputs "input_audio" \
# --height 256 \
@@ -21,8 +23,8 @@
# 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 \
--dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited \
--dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2-T2AV-splited/metadata.csv \
--data_file_keys "video,input_audio" \
--extra_inputs "input_audio" \
--height 512 \

6
examples/ltx2/model_training/lora/LTX-2.3-I2AV-splited.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.3-I2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
# 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 \
--dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.3-I2AV-splited \
--dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.3-I2AV-splited/metadata.csv \
--data_file_keys "video,input_audio" \
--extra_inputs "input_audio,input_image" \
--height 512 \

6
examples/ltx2/model_training/lora/LTX-2.3-T2AV-IC-LoRA-splited.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.3-T2AV-IC-LoRA-splited/*" --local_dir ./data/diffsynth_example_dataset
# 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_iclora.json \
--dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-IC-LoRA-splited \
--dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-IC-LoRA-splited/metadata.json \
--data_file_keys "video,input_audio,in_context_videos" \
--extra_inputs "input_audio,in_context_videos,in_context_downsample_factor,frame_rate" \
--height 512 \

6
examples/ltx2/model_training/lora/LTX-2.3-T2AV-splited.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "ltx2/LTX-2.3-T2AV-splited/*" --local_dir ./data/diffsynth_example_dataset
# 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 \
--dataset_base_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-splited \
--dataset_metadata_path data/diffsynth_example_dataset/ltx2/LTX-2.3-T2AV-splited/metadata.csv \
--data_file_keys "video,input_audio" \
--extra_inputs "input_audio" \
--height 512 \