File size: 7,144 Bytes
f1069cc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
import argparse
import io

import requests
import torch
from omegaconf import OmegaConf

from diffusers import AutoencoderKL
from diffusers.pipelines.stable_diffusion.convert_from_ckpt import (
    assign_to_checkpoint,
    conv_attn_to_linear,
    create_vae_diffusers_config,
    renew_vae_attention_paths,
    renew_vae_resnet_paths,
)


def custom_convert_ldm_vae_checkpoint(checkpoint, config):
    vae_state_dict = checkpoint

    new_checkpoint = {}

    new_checkpoint["encoder.conv_in.weight"] = vae_state_dict["encoder.conv_in.weight"]
    new_checkpoint["encoder.conv_in.bias"] = vae_state_dict["encoder.conv_in.bias"]
    new_checkpoint["encoder.conv_out.weight"] = vae_state_dict["encoder.conv_out.weight"]
    new_checkpoint["encoder.conv_out.bias"] = vae_state_dict["encoder.conv_out.bias"]
    new_checkpoint["encoder.conv_norm_out.weight"] = vae_state_dict["encoder.norm_out.weight"]
    new_checkpoint["encoder.conv_norm_out.bias"] = vae_state_dict["encoder.norm_out.bias"]

    new_checkpoint["decoder.conv_in.weight"] = vae_state_dict["decoder.conv_in.weight"]
    new_checkpoint["decoder.conv_in.bias"] = vae_state_dict["decoder.conv_in.bias"]
    new_checkpoint["decoder.conv_out.weight"] = vae_state_dict["decoder.conv_out.weight"]
    new_checkpoint["decoder.conv_out.bias"] = vae_state_dict["decoder.conv_out.bias"]
    new_checkpoint["decoder.conv_norm_out.weight"] = vae_state_dict["decoder.norm_out.weight"]
    new_checkpoint["decoder.conv_norm_out.bias"] = vae_state_dict["decoder.norm_out.bias"]

    new_checkpoint["quant_conv.weight"] = vae_state_dict["quant_conv.weight"]
    new_checkpoint["quant_conv.bias"] = vae_state_dict["quant_conv.bias"]
    new_checkpoint["post_quant_conv.weight"] = vae_state_dict["post_quant_conv.weight"]
    new_checkpoint["post_quant_conv.bias"] = vae_state_dict["post_quant_conv.bias"]

    # Retrieves the keys for the encoder down blocks only
    num_down_blocks = len({".".join(layer.split(".")[:3]) for layer in vae_state_dict if "encoder.down" in layer})
    down_blocks = {
        layer_id: [key for key in vae_state_dict if f"down.{layer_id}" in key] for layer_id in range(num_down_blocks)
    }

    # Retrieves the keys for the decoder up blocks only
    num_up_blocks = len({".".join(layer.split(".")[:3]) for layer in vae_state_dict if "decoder.up" in layer})
    up_blocks = {
        layer_id: [key for key in vae_state_dict if f"up.{layer_id}" in key] for layer_id in range(num_up_blocks)
    }

    for i in range(num_down_blocks):
        resnets = [key for key in down_blocks[i] if f"down.{i}" in key and f"down.{i}.downsample" not in key]

        if f"encoder.down.{i}.downsample.conv.weight" in vae_state_dict:
            new_checkpoint[f"encoder.down_blocks.{i}.downsamplers.0.conv.weight"] = vae_state_dict.pop(
                f"encoder.down.{i}.downsample.conv.weight"
            )
            new_checkpoint[f"encoder.down_blocks.{i}.downsamplers.0.conv.bias"] = vae_state_dict.pop(
                f"encoder.down.{i}.downsample.conv.bias"
            )

        paths = renew_vae_resnet_paths(resnets)
        meta_path = {"old": f"down.{i}.block", "new": f"down_blocks.{i}.resnets"}
        assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)

    mid_resnets = [key for key in vae_state_dict if "encoder.mid.block" in key]
    num_mid_res_blocks = 2
    for i in range(1, num_mid_res_blocks + 1):
        resnets = [key for key in mid_resnets if f"encoder.mid.block_{i}" in key]

        paths = renew_vae_resnet_paths(resnets)
        meta_path = {"old": f"mid.block_{i}", "new": f"mid_block.resnets.{i - 1}"}
        assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)

    mid_attentions = [key for key in vae_state_dict if "encoder.mid.attn" in key]
    paths = renew_vae_attention_paths(mid_attentions)
    meta_path = {"old": "mid.attn_1", "new": "mid_block.attentions.0"}
    assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)
    conv_attn_to_linear(new_checkpoint)

    for i in range(num_up_blocks):
        block_id = num_up_blocks - 1 - i
        resnets = [
            key for key in up_blocks[block_id] if f"up.{block_id}" in key and f"up.{block_id}.upsample" not in key
        ]

        if f"decoder.up.{block_id}.upsample.conv.weight" in vae_state_dict:
            new_checkpoint[f"decoder.up_blocks.{i}.upsamplers.0.conv.weight"] = vae_state_dict[
                f"decoder.up.{block_id}.upsample.conv.weight"
            ]
            new_checkpoint[f"decoder.up_blocks.{i}.upsamplers.0.conv.bias"] = vae_state_dict[
                f"decoder.up.{block_id}.upsample.conv.bias"
            ]

        paths = renew_vae_resnet_paths(resnets)
        meta_path = {"old": f"up.{block_id}.block", "new": f"up_blocks.{i}.resnets"}
        assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)

    mid_resnets = [key for key in vae_state_dict if "decoder.mid.block" in key]
    num_mid_res_blocks = 2
    for i in range(1, num_mid_res_blocks + 1):
        resnets = [key for key in mid_resnets if f"decoder.mid.block_{i}" in key]

        paths = renew_vae_resnet_paths(resnets)
        meta_path = {"old": f"mid.block_{i}", "new": f"mid_block.resnets.{i - 1}"}
        assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)

    mid_attentions = [key for key in vae_state_dict if "decoder.mid.attn" in key]
    paths = renew_vae_attention_paths(mid_attentions)
    meta_path = {"old": "mid.attn_1", "new": "mid_block.attentions.0"}
    assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)
    conv_attn_to_linear(new_checkpoint)
    return new_checkpoint


def vae_pt_to_vae_diffuser(
    checkpoint_path: str,
    output_path: str,
):
    # Only support V1
    r = requests.get(
        " https://raw.githubusercontent.com/CompVis/stable-diffusion/main/configs/stable-diffusion/v1-inference.yaml"
    )
    io_obj = io.BytesIO(r.content)

    original_config = OmegaConf.load(io_obj)
    image_size = 512
    device = "cuda" if torch.cuda.is_available() else "cpu"
    checkpoint = torch.load(checkpoint_path, map_location=device)

    # Convert the VAE model.
    vae_config = create_vae_diffusers_config(original_config, image_size=image_size)
    converted_vae_checkpoint = custom_convert_ldm_vae_checkpoint(checkpoint["state_dict"], vae_config)

    vae = AutoencoderKL(**vae_config)
    vae.load_state_dict(converted_vae_checkpoint)
    vae.save_pretrained(output_path)


if __name__ == "__main__":
    parser = argparse.ArgumentParser()

    parser.add_argument("--vae_pt_path", default=None, type=str, required=True, help="Path to the VAE.pt to convert.")
    parser.add_argument("--dump_path", default=None, type=str, required=True, help="Path to the VAE.pt to convert.")

    args = parser.parse_args()

    vae_pt_to_vae_diffuser(args.vae_pt_path, args.dump_path)