update

trainer.py

@@ -138,8 +138,8 @@ class Trainer:
 
         # command = f'accelerate launch Tune-A-Video/train_tuneavideo.py --config {config_path}'
         # command = f'accelerate launch Video-P2P/run_tuning.py --config {config_path}'
-        command = f'accelerate launch Video-P2P/train_tuneavideo.py --config {config_path}'
-        # command = f'accelerate launch Tune-A-Video-debug/train_tuneavideo.py --config {config_path}'
+        # command = f'accelerate launch Video-P2P/train_tuneavideo.py --config {config_path}'
+        command = f'accelerate launch Tune-A-Video-debug/train_tuneavideo.py --config {config_path}'
         subprocess.run(shlex.split(command))
         save_model_card(save_dir=output_dir,
                         base_model=base_model,

utils.py

@@ -45,10 +45,11 @@ tags:
 - diffusers
 - text-to-video
 - tune-a-video
+- video-p2p
 inference: false
 ---
 
-# Tune-A-Video - {save_dir.name}
+# Video-P2P - {save_dir.name}
 
 ## Model description
 - Base model: [{base_model}](https://huggingface.co/{base_model})
@@ -57,6 +58,7 @@ inference: false
 {image_str}
 
 ## Related papers:
+- [Video-P2P](https://arxiv.org/abs/2303.04761): Video editing with cross-attention control
 - [Tune-A-Video](https://arxiv.org/abs/2212.11565): One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
 - [Stable-Diffusion](https://arxiv.org/abs/2112.10752): High-Resolution Image Synthesis with Latent Diffusion Models
 '''