Function get_ltx2_connectors_config

scripts/convert_ltx2_to_diffusers.py:373–451

(version: str)

def get_ltx2_connectors_config(version: str) -> tuple[dict[str, Any], dict[str, Any], dict[str, Any]]:
    if version == "test":
        config = {
            "model_id": "diffusers-internal-dev/dummy-ltx2",
            "diffusers_config": {
                "caption_channels": 16,
                "text_proj_in_factor": 3,
                "video_connector_num_attention_heads": 4,
                "video_connector_attention_head_dim": 8,
                "video_connector_num_layers": 1,
                "video_connector_num_learnable_registers": None,
                "audio_connector_num_attention_heads": 4,
                "audio_connector_attention_head_dim": 8,
                "audio_connector_num_layers": 1,
                "audio_connector_num_learnable_registers": None,
                "connector_rope_base_seq_len": 32,
                "rope_theta": 10000.0,
                "rope_double_precision": False,
                "causal_temporal_positioning": False,
            },
        }
    elif version == "2.0":
        config = {
            "model_id": "Lightricks/LTX-2",
            "diffusers_config": {
                "caption_channels": 3840,
                "text_proj_in_factor": 49,
                "video_connector_num_attention_heads": 30,
                "video_connector_attention_head_dim": 128,
                "video_connector_num_layers": 2,
                "video_connector_num_learnable_registers": 128,
                "video_gated_attn": False,
                "audio_connector_num_attention_heads": 30,
                "audio_connector_attention_head_dim": 128,
                "audio_connector_num_layers": 2,
                "audio_connector_num_learnable_registers": 128,
                "audio_gated_attn": False,
                "connector_rope_base_seq_len": 4096,
                "rope_theta": 10000.0,
                "rope_double_precision": True,
                "causal_temporal_positioning": False,
                "rope_type": "split",
                "per_modality_projections": False,
                "proj_bias": False,
            },
        }
        rename_dict = LTX_2_0_CONNECTORS_KEYS_RENAME_DICT
        special_keys_remap = LTX_2_0_CONNECTORS_SPECIAL_KEYS_REMAP
    elif version == "2.3":
        config = {
            "model_id": "Lightricks/LTX-2.3",
            "diffusers_config": {
                "caption_channels": 3840,
                "text_proj_in_factor": 49,
                "video_connector_num_attention_heads": 32,
                "video_connector_attention_head_dim": 128,
                "video_connector_num_layers": 8,
                "video_connector_num_learnable_registers": 128,