| pretrained_model_path: "./checkpoints/stable-diffusion-v1-4" | |
| output_dir: "./outputs/man-surfing" | |
| train_data: | |
| video_path: "data/man-surfing.mp4" | |
| prompt: "a man is surfing" | |
| n_sample_frames: 24 | |
| width: 512 | |
| height: 512 | |
| sample_start_idx: 0 | |
| sample_frame_rate: 1 | |
| validation_data: | |
| prompts: | |
| - "a panda is surfing" | |
| - "a boy, wearing a birthday hat, is surfing" | |
| - "a raccoon is surfing, cartoon style" | |
| - "Iron Man is surfing in the desert" | |
| video_length: 24 | |
| width: 512 | |
| height: 512 | |
| num_inference_steps: 50 | |
| guidance_scale: 12.5 | |
| use_inv_latent: True | |
| num_inv_steps: 50 | |
| learning_rate: 3e-5 | |
| train_batch_size: 1 | |
| max_train_steps: 500 | |
| checkpointing_steps: 1000 | |
| validation_steps: 100 | |
| trainable_modules: | |
| - "attn1.to_q" | |
| - "attn2.to_q" | |
| - "attn_temp" | |
| seed: 33 | |
| mixed_precision: fp16 | |
| use_8bit_adam: False | |
| gradient_checkpointing: True | |
| enable_xformers_memory_efficient_attention: True | |