Function convert_ldm_unet_checkpoint

diffusers/scripts/convert_if.py:298–536

Takes a state dict and a config, and returns a converted checkpoint.

(unet_state_dict, config, path=None)

def convert_ldm_unet_checkpoint(unet_state_dict, config, path=None):
    """
    Takes a state dict and a config, and returns a converted checkpoint.
    """
    new_checkpoint = {}

    new_checkpoint["time_embedding.linear_1.weight"] = unet_state_dict["time_embed.0.weight"]
    new_checkpoint["time_embedding.linear_1.bias"] = unet_state_dict["time_embed.0.bias"]
    new_checkpoint["time_embedding.linear_2.weight"] = unet_state_dict["time_embed.2.weight"]
    new_checkpoint["time_embedding.linear_2.bias"] = unet_state_dict["time_embed.2.bias"]

    if config["class_embed_type"] in [None, "identity"]:
        # No parameters to port
        ...
    elif config["class_embed_type"] == "timestep" or config["class_embed_type"] == "projection":
        new_checkpoint["class_embedding.linear_1.weight"] = unet_state_dict["label_emb.0.0.weight"]
        new_checkpoint["class_embedding.linear_1.bias"] = unet_state_dict["label_emb.0.0.bias"]
        new_checkpoint["class_embedding.linear_2.weight"] = unet_state_dict["label_emb.0.2.weight"]
        new_checkpoint["class_embedding.linear_2.bias"] = unet_state_dict["label_emb.0.2.bias"]
    else:
        raise NotImplementedError(f"Not implemented `class_embed_type`: {config['class_embed_type']}")

    new_checkpoint["conv_in.weight"] = unet_state_dict["input_blocks.0.0.weight"]
    new_checkpoint["conv_in.bias"] = unet_state_dict["input_blocks.0.0.bias"]

    new_checkpoint["conv_norm_out.weight"] = unet_state_dict["out.0.weight"]
    new_checkpoint["conv_norm_out.bias"] = unet_state_dict["out.0.bias"]
    new_checkpoint["conv_out.weight"] = unet_state_dict["out.2.weight"]
    new_checkpoint["conv_out.bias"] = unet_state_dict["out.2.bias"]

    # Retrieves the keys for the input blocks only
    num_input_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "input_blocks" in layer})
    input_blocks = {
        layer_id: [key for key in unet_state_dict if f"input_blocks.{layer_id}." in key]
        for layer_id in range(num_input_blocks)
    }

    # Retrieves the keys for the middle blocks only
    num_middle_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "middle_block" in layer})
    middle_blocks = {
        layer_id: [key for key in unet_state_dict if f"middle_block.{layer_id}" in key]
        for layer_id in range(num_middle_blocks)
    }

    # Retrieves the keys for the output blocks only
    num_output_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "output_blocks" in layer})
    output_blocks = {
        layer_id: [key for key in unet_state_dict if f"output_blocks.{layer_id}." in key]
        for layer_id in range(num_output_blocks)
    }

    for i in range(1, num_input_blocks):
        block_id = (i - 1) // (config["layers_per_block"] + 1)
        layer_in_block_id = (i - 1) % (config["layers_per_block"] + 1)

        resnets = [
            key for key in input_blocks[i] if f"input_blocks.{i}.0" in key and f"input_blocks.{i}.0.op" not in key
        ]