Function convert_ltx2_video_vae

scripts/convert_ltx2_to_diffusers.py:628–653

(
    original_state_dict: dict[str, Any], version: str, timestep_conditioning: bool
)

def convert_ltx2_video_vae(
    original_state_dict: dict[str, Any], version: str, timestep_conditioning: bool
) -> dict[str, Any]:
    config, rename_dict, special_keys_remap = get_ltx2_video_vae_config(version, timestep_conditioning)
    diffusers_config = config["diffusers_config"]

    with init_empty_weights():
        vae = AutoencoderKLLTX2Video.from_config(diffusers_config)

    # Handle official code --> diffusers key remapping via the remap dict
    for key in list(original_state_dict.keys()):
        new_key = key[:]
        for replace_key, rename_key in rename_dict.items():
            new_key = new_key.replace(replace_key, rename_key)
        update_state_dict_inplace(original_state_dict, key, new_key)

    # Handle any special logic which can't be expressed by a simple 1:1 remapping with the handlers in
    # special_keys_remap
    for key in list(original_state_dict.keys()):
        for special_key, handler_fn_inplace in special_keys_remap.items():
            if special_key not in key:
                continue
            handler_fn_inplace(key, original_state_dict)

    vae.load_state_dict(original_state_dict, strict=True, assign=True)
    return vae


def get_ltx2_audio_vae_config(version: str) -> tuple[dict[str, Any], dict[str, Any], dict[str, Any]]: