Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

.sh files error fixed #111

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions scripts/run.sh
Original file line number Diff line number Diff line change
Expand Up @@ -8,21 +8,21 @@ config=configs/inference_$1_v1.0.yaml
prompt_dir=prompts/$1/
res_dir="results"

if [ "$1" == "256" ]; then
if [ "$1" = "256" ]; then
H=256
FS=3 ## This model adopts frame stride=3, range recommended: 1-6 (larger value -> larger motion)
elif [ "$1" == "512" ]; then
elif [ "$1" = "512" ]; then
H=320
FS=24 ## This model adopts FPS=24, range recommended: 15-30 (smaller value -> larger motion)
elif [ "$1" == "1024" ]; then
elif [ "$1" = "1024" ]; then
H=576
FS=10 ## This model adopts FPS=10, range recommended: 15-5 (smaller value -> larger motion)
else
echo "Invalid input. Please enter 256, 512, or 1024."
exit 1
fi

if [ "$1" == "256" ]; then
if [ "$1" = "256" ]; then
CUDA_VISIBLE_DEVICES=0 python3 scripts/evaluation/inference.py \
--seed ${seed} \
--ckpt_path $ckpt \
Expand Down Expand Up @@ -58,4 +58,4 @@ fi

## multi-cond CFG: the <unconditional_guidance_scale> is s_txt, <cfg_img> is s_img
#--multiple_cond_cfg --cfg_img 7.5
#--loop
#--loop
2 changes: 1 addition & 1 deletion scripts/run_application.sh
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ res_dir="results"
FS=5 ## This model adopts FPS=5, range recommended: 5-30 (smaller value -> larger motion)


if [ "$1" == "interp" ]; then
if [ "$1" = "interp" ]; then
seed=12306
name=dynamicrafter_512_$1_seed${seed}
CUDA_VISIBLE_DEVICES=0 python3 scripts/evaluation/inference.py \
Expand Down
10 changes: 5 additions & 5 deletions scripts/run_mp.sh
Original file line number Diff line number Diff line change
Expand Up @@ -9,13 +9,13 @@ config=configs/inference_$1_v1.0.yaml
prompt_dir=prompts/$1/
res_dir="results"

if [ "$1" == "256" ]; then
if [ "$1" = "256" ]; then
H=256
FS=3 ## This model adopts frame stride=3
elif [ "$1" == "512" ]; then
elif [ "$1" = "512" ]; then
H=320
FS=24 ## This model adopts FPS=24
elif [ "$1" == "1024" ]; then
elif [ "$1" = "1024" ]; then
H=576
FS=10 ## This model adopts FPS=10
else
Expand Down Expand Up @@ -62,7 +62,7 @@ fi
#--loop

## inference using single node with multi-GPUs:
if [ "$1" == "256" ]; then
if [ "$1" = "256" ]; then
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 -m torch.distributed.launch \
--nproc_per_node=8 --nnodes=1 --master_addr=127.0.0.1 --master_port=23456 --node_rank=0 \
scripts/evaluation/ddp_wrapper.py \
Expand Down Expand Up @@ -99,4 +99,4 @@ scripts/evaluation/ddp_wrapper.py \
--video_length 16 \
--frame_stride ${FS} \
--timestep_spacing 'uniform_trailing' --guidance_rescale 0.7 --perframe_ae
fi
fi