transformer/config.json

{
    "in_channels": 16,
    "out_channels": 16,
    "num_attention_heads": 24,
    "attention_head_dim": 128,
    "num_layers": 20,
    "num_single_layers": 40,
    "num_refiner_layers": 2,
    "mlp_ratio": 4.0,
    "patch_size": 2,
    "patch_size_t": 1,
    "qk_norm": "rms_norm",
    "guidance_embeds": true,
    "text_embed_dim": 4096,
    "pooled_projection_dim": 768,
    "rope_theta": 256.0,
    "rope_axes_dim": [
        16,
        56,
        56
    ],
    "_class_name": "HunyuanVideoTransformer3DModel",
    "_diffusers_version": "0.32.0.dev0",
    "_name_or_path": "/m2v_intern2/zhenglin/paper_assets/hf_cache/hub/models--hunyuanvideo-community--HunyuanVideo/snapshots/e8c2aaa66fe3742a32c11a6766aecbf07c56e773"
}