| # data | |
| file_path: './data/music.mp4' | |
| save_path: './output/music/' | |
| mininterv: 10 # for keyframe selection | |
| maxinterv: 30 # for keyframe selection | |
| # diffusion | |
| seed: 0 | |
| prompt: 'A beautiful woman with headphones listening to music in CG cyberpunk style, neon, closed eyes, colorful' | |
| sd_path: 'stablediffusionapi/rev-animated' | |
| use_controlnet: True | |
| controlnet_type: 'hed' # 'depth', 'canny' | |
| cond_scale: 1.0 | |
| use_freeu: False | |
| # video-to-video translation | |
| batch_size: 8 | |
| num_inference_steps: 20 | |
| num_warmup_steps: 3 | |
| end_opt_step: 15 | |
| run_ebsynth: False | |
| max_process: 4 | |
| # supporting model | |
| gmflow_path: './model/gmflow_sintel-0c07dcb3.pth' | |
| sod_path: './model/epoch_resnet.pth' | |
| use_salinecy: True |