Skip to content
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
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -189,7 +189,7 @@ We list the inference scripts for different tasks mentioned in our paper as foll
<img width="800" src="assets/boy_and_mom.gif"/>
<br>

We currently implemented multi-condition control on **I2VGen-XL**. The following checkpoint are trained on 7 control conditions, including depth, canny, normal, softedge, segmentation, lineart, and openpose. Here are the sample inference scripts that uses depth, canny, segmentation, and openpose as control conditions.
We currently implemented multi-condition control on **I2VGen-XL**. The following checkpoints are trained on 7 control conditions, including depth, canny, normal, softedge, segmentation, lineart, and openpose. Here are the sample inference scripts that use depth, canny, segmentation, and openpose as control conditions.

| Adapter Checkpoint | Router Checkpoint | Inference (w/ extracted condition) | Inference (w/o extracted condition) |
|-----------|------|---------|--------|
Expand Down
2 changes: 1 addition & 1 deletion inference.py
Original file line number Diff line number Diff line change
Expand Up @@ -261,7 +261,7 @@ def inference_main(inference_args):
# create dir for condition images/frames
output_condition_images_dir = []
for i, ctrl_type in enumerate(inference_args.control_types):
output_condition_images_dir.append(os.path.join(output_dir, f"conditon_{ctrl_type}_{inference_args.eval_input_type}"))
output_condition_images_dir.append(os.path.join(output_dir, f"condition_{ctrl_type}_{inference_args.eval_input_type}"))
os.makedirs(output_condition_images_dir[-1], exist_ok=True)

if inference_args.extract_control_conditions or inference_args.eval_input_type == 'frames':
Expand Down