| |
| |
| infra: |
| expected_world_size: 16 |
| expected_nodes: 2 |
| expected_gpus_per_node: 8 |
| required_gpu_name: H100 |
| sharding_strategy: hybrid_full |
| mixed_precision: true |
| vae_dtype: float32 |
| gradient_checkpointing: true |
| generator_fsdp_wrap_strategy: size |
| real_score_fsdp_wrap_strategy: size |
| fake_score_fsdp_wrap_strategy: size |
| text_encoder_fsdp_wrap_strategy: size |
| model_kwargs: |
| model_name: Wan2.2-TI2V-5B |
| fun_control_model_path: models/Wan2.2-Fun-5B-Control |
| timestep_shift: 5.0 |
| num_frame_per_block: 8 |
| local_attn_size: -1 |
| control_raw_frames: 93 |
| checkpoints: |
| generator_ckpt: null |
| real_score_ckpt: null |
| fake_score_ckpt: null |
| algorithm: |
| trainer: score_distillation |
| distribution_loss: dmd |
| generator_is_causal: false |
| real_score_is_causal: false |
| fake_score_is_causal: false |
| all_causal: false |
| backward_simulation: true |
| independent_first_frame: false |
| ts_schedule: false |
| real_guidance_scale: 3.0 |
| fake_guidance_scale: 0.0 |
| training: |
| lr: 1.0e-05 |
| lr_critic: 2.0e-06 |
| weight_decay: 0.0 |
| beta1: 0.0 |
| beta2: 0.999 |
| beta1_critic: 0.0 |
| beta2_critic: 0.999 |
| batch_size: 1 |
| gradient_accumulation_steps: 2 |
| ema_weight: 0.99 |
| ema_start_step: 200 |
| log_iters: 100 |
| max_checkpoints: 20 |
| max_iters: 3000 |
| gc_interval: 100 |
| dfake_gen_update_ratio: 5 |
| min_num_training_frames: 24 |
| num_training_frames: 24 |
| slice_last_frames: 24 |
| data: |
| data_path: data/depth_video_5k/manifest.jsonl |
| eval_data_path: data/depth_video_5k/manifest.jsonl |
| control_manifest: data/depth_video_5k/manifest.jsonl |
| eval_control_manifest: data/depth_video_5k/manifest.jsonl |
| control_raw_frames: 93 |
| control_min_temporal_difference: 0.0001 |
| control_num_workers: 2 |
| image_or_video_shape: |
| - 1 |
| - 24 |
| - 48 |
| - 30 |
| - 52 |
| full_ref_mode: zero_through_ref_conv |
| inference: |
| sampling_steps: 4 |
| guidance_scale: 1.0 |
| inference_guidance_scale: 1.0 |
| sink_size: 0 |
| multi_shot_rope_offset: 0 |
| evaluation: |
| interval: -1 |
| num_frames: 24 |
| use_ema: false |
| val_batch_size: 1 |
| save_latents_only: true |
| adapter: |
| type: lora |
| rank: 64 |
| alpha: 64 |
| dropout: 0.0 |
| apply_to_critic: true |
| verbose: false |
| logging: |
| seed: 17 |
| wandb_entity: null |
| wandb_project: LongLive-WanFun5B-Control-DMD |
|
|
