How should I set up a "run_text2video Bash" file to obtain the output described in the videocrafter2 paper?

[HangyeolLee12]

hello,

I used the text from the paper as an input prompt to run the t2v 320*512 model (videocrafter2), but the results are different from those in the paper.

I used below bash file.

What settings should I change to obtain the same video as in the paper?

Thanks

===========================================
<run_text2video Bash file>
name="base_512_v2"
ckpt='checkpoints/base_512_v2/model.ckpt'
config='configs/inference_t2v_512_v2.0.yaml'

prompt_file="prompts/test_prompts.txt"
res_dir="results"
python3 scripts/evaluation/inference.py
--seed 123
--mode 'base'
--ckpt_path $ckpt
--config $config
--savedir $res_dir/$name
--n_samples 1
--bs 1 --height 320 --width 512
--unconditional_guidance_scale 12.0
--ddim_steps 50
--ddim_eta 1.0
--prompt_file $prompt_file
--fps 28

=====================================