mirror of
https://github.com/storytold/FineTrainers-Conditioning.git
synced 2026-10-09 00:09:45 +00:00
Aryan
ee02219eac
* refactor * update * update * Update README.md Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> * Update README.md Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> * address review comments part i * fix adapter name causing peft error * prompts -> prompt * update * add video * update --------- Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
47 lines
1.3 KiB
Bash
Executable File
47 lines
1.3 KiB
Bash
Executable File
#!/bin/bash
|
|
|
|
MODEL_ID="THUDM/CogVideoX-2b"
|
|
|
|
NUM_GPUS=8
|
|
|
|
# For more details on the expected data format, please refer to the README.
|
|
DATA_ROOT="/path/to/my/datasets/video-dataset" # This needs to be the path to the base directory where your videos are located.
|
|
CAPTION_COLUMN="prompt.txt"
|
|
VIDEO_COLUMN="videos.txt"
|
|
OUTPUT_DIR="/path/to/my/datasets/preprocessed-dataset"
|
|
HEIGHT=480
|
|
WIDTH=720
|
|
MAX_NUM_FRAMES=49
|
|
MAX_SEQUENCE_LENGTH=226
|
|
TARGET_FPS=8
|
|
BATCH_SIZE=1
|
|
DTYPE=fp32
|
|
|
|
# To create a folder-style dataset structure without pre-encoding videos and captions
|
|
# For Image-to-Video finetuning, make sure to pass `--save_image_latents`
|
|
CMD_WITHOUT_PRE_ENCODING="\
|
|
torchrun --nproc_per_node=$NUM_GPUS \
|
|
training/prepare_dataset.py \
|
|
--model_id $MODEL_ID \
|
|
--data_root $DATA_ROOT \
|
|
--caption_column $CAPTION_COLUMN \
|
|
--video_column $VIDEO_COLUMN \
|
|
--output_dir $OUTPUT_DIR \
|
|
--height $HEIGHT \
|
|
--width $WIDTH \
|
|
--max_num_frames $MAX_NUM_FRAMES \
|
|
--max_sequence_length $MAX_SEQUENCE_LENGTH \
|
|
--target_fps $TARGET_FPS \
|
|
--batch_size $BATCH_SIZE \
|
|
--dtype $DTYPE
|
|
"
|
|
|
|
CMD_WITH_PRE_ENCODING="$CMD_WITHOUT_PRE_ENCODING --save_tensors"
|
|
|
|
# Select which you'd like to run
|
|
CMD=$CMD_WITH_PRE_ENCODING
|
|
|
|
echo "===== Running \`$CMD\` ====="
|
|
eval $CMD
|
|
echo -ne "===== Finished running script =====\n"
|