| { |
| "model_config": { |
| "model_name": "videodit_ardf", |
| "num_layers": 34, |
| "hidden_size": 3072, |
| "ffn_hidden_size": 12288, |
| "num_attention_heads": 24, |
| "num_query_groups": 8, |
| "kv_channels": 128, |
| "layernorm_epsilon": 1e-06, |
| "apply_layernorm_1p": true, |
| "x_rescale_factor": 1, |
| "half_channel_vae": false, |
| "params_dtype": "torch.bfloat16", |
| "patch_size": 2, |
| "t_patch_size": 1, |
| "in_channels": 16, |
| "out_channels": 16, |
| "cond_hidden_ratio": 0.25, |
| "caption_channels": 4096, |
| "caption_max_length": 800, |
| "xattn_cond_hidden_ratio": 1.0, |
| "cond_gating_ratio": 1.0, |
| "gated_linear_unit": false |
| }, |
| "runtime_config": { |
| "cfg_number": 1, |
| "cfg_t_range": [ |
| 0.0, |
| 0.0217, |
| 0.1, |
| 0.3, |
| 0.999 |
| ], |
| "prev_chunk_scales": [ |
| 1.5, |
| 1.5, |
| 1.5, |
| 1.0, |
| 1.0 |
| ], |
| "text_scales": [ |
| 7.5, |
| 7.5, |
| 7.5, |
| 0.0, |
| 0.0 |
| ], |
| "noise2clean_kvrange": [], |
| "clean_chunk_kvrange": 1, |
| "clean_t": 0.9999, |
| "seed": 1234, |
| "num_frames": 240, |
| "video_size_h": 720, |
| "video_size_w": 720, |
| "num_steps": 16, |
| "window_size": 4, |
| "fps": 24, |
| "chunk_width": 6, |
| "load": "/path/to/your/MAGI-1/checkpoint/4.5B_distill", |
| "t5_pretrained": "/path/to/your/t5/safetensor", |
| "t5_device": "cuda", |
| "vae_pretrained": "/path/to/your/vae/checkpoint", |
| "scale_factor": 0.18215, |
| "temporal_downsample_factor": 4 |
| }, |
| "engine_config": { |
| "distributed_backend": "nccl", |
| "distributed_timeout_minutes": 15, |
| "pp_size": 1, |
| "cp_size": 1, |
| "cp_strategy": "none", |
| "ulysses_overlap_degree": 1, |
| "fp8_quant": false, |
| "distill_nearly_clean_chunk_threshold": 0.3, |
| "shortcut_mode": "8,16,16", |
| "distill": true, |
| "kv_offload": true, |
| "enable_cuda_graph": false |
| } |
| } |
