File size: 7,020 Bytes
7926358
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
# coding=utf-8
# Copyright 2024 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Conversion script for the LDM checkpoints."""

import argparse
import importlib

import torch

from diffusers.pipelines.stable_diffusion.convert_from_ckpt import download_from_original_stable_diffusion_ckpt


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

    parser.add_argument(
        "--checkpoint_path", default=None, type=str, required=True, help="Path to the checkpoint to convert."
    )
    # !wget https://raw.githubusercontent.com/CompVis/stable-diffusion/main/configs/stable-diffusion/v1-inference.yaml
    parser.add_argument(
        "--original_config_file",
        default=None,
        type=str,
        help="The YAML config file corresponding to the original architecture.",
    )
    parser.add_argument(
        "--config_files",
        default=None,
        type=str,
        help="The YAML config file corresponding to the architecture.",
    )
    parser.add_argument(
        "--num_in_channels",
        default=None,
        type=int,
        help="The number of input channels. If `None` number of input channels will be automatically inferred.",
    )
    parser.add_argument(
        "--scheduler_type",
        default="pndm",
        type=str,
        help="Type of scheduler to use. Should be one of ['pndm', 'lms', 'ddim', 'euler', 'euler-ancestral', 'dpm']",
    )
    parser.add_argument(
        "--pipeline_type",
        default=None,
        type=str,
        help=(
            "The pipeline type. One of 'FrozenOpenCLIPEmbedder', 'FrozenCLIPEmbedder', 'PaintByExample'"
            ". If `None` pipeline will be automatically inferred."
        ),
    )
    parser.add_argument(
        "--image_size",
        default=None,
        type=int,
        help=(
            "The image size that the model was trained on. Use 512 for Stable Diffusion v1.X and Stable Siffusion v2"
            " Base. Use 768 for Stable Diffusion v2."
        ),
    )
    parser.add_argument(
        "--prediction_type",
        default=None,
        type=str,
        help=(
            "The prediction type that the model was trained on. Use 'epsilon' for Stable Diffusion v1.X and Stable"
            " Diffusion v2 Base. Use 'v_prediction' for Stable Diffusion v2."
        ),
    )
    parser.add_argument(
        "--extract_ema",
        action="store_true",
        help=(
            "Only relevant for checkpoints that have both EMA and non-EMA weights. Whether to extract the EMA weights"
            " or not. Defaults to `False`. Add `--extract_ema` to extract the EMA weights. EMA weights usually yield"
            " higher quality images for inference. Non-EMA weights are usually better to continue fine-tuning."
        ),
    )
    parser.add_argument(
        "--upcast_attention",
        action="store_true",
        help=(
            "Whether the attention computation should always be upcasted. This is necessary when running stable"
            " diffusion 2.1."
        ),
    )
    parser.add_argument(
        "--from_safetensors",
        action="store_true",
        help="If `--checkpoint_path` is in `safetensors` format, load checkpoint with safetensors instead of PyTorch.",
    )
    parser.add_argument(
        "--to_safetensors",
        action="store_true",
        help="Whether to store pipeline in safetensors format or not.",
    )
    parser.add_argument("--dump_path", default=None, type=str, required=True, help="Path to the output model.")
    parser.add_argument("--device", type=str, help="Device to use (e.g. cpu, cuda:0, cuda:1, etc.)")
    parser.add_argument(
        "--stable_unclip",
        type=str,
        default=None,
        required=False,
        help="Set if this is a stable unCLIP model. One of 'txt2img' or 'img2img'.",
    )
    parser.add_argument(
        "--stable_unclip_prior",
        type=str,
        default=None,
        required=False,
        help="Set if this is a stable unCLIP txt2img model. Selects which prior to use. If `--stable_unclip` is set to `txt2img`, the karlo prior (https://huggingface.co/kakaobrain/karlo-v1-alpha/tree/main/prior) is selected by default.",
    )
    parser.add_argument(
        "--clip_stats_path",
        type=str,
        help="Path to the clip stats file. Only required if the stable unclip model's config specifies `model.params.noise_aug_config.params.clip_stats_path`.",
        required=False,
    )
    parser.add_argument(
        "--controlnet", action="store_true", default=None, help="Set flag if this is a controlnet checkpoint."
    )
    parser.add_argument("--half", action="store_true", help="Save weights in half precision.")
    parser.add_argument(
        "--vae_path",
        type=str,
        default=None,
        required=False,
        help="Set to a path, hub id to an already converted vae to not convert it again.",
    )
    parser.add_argument(
        "--pipeline_class_name",
        type=str,
        default=None,
        required=False,
        help="Specify the pipeline class name",
    )

    args = parser.parse_args()

    if args.pipeline_class_name is not None:
        library = importlib.import_module("diffusers")
        class_obj = getattr(library, args.pipeline_class_name)
        pipeline_class = class_obj
    else:
        pipeline_class = None

    pipe = download_from_original_stable_diffusion_ckpt(
        checkpoint_path_or_dict=args.checkpoint_path,
        original_config_file=args.original_config_file,
        config_files=args.config_files,
        image_size=args.image_size,
        prediction_type=args.prediction_type,
        model_type=args.pipeline_type,
        extract_ema=args.extract_ema,
        scheduler_type=args.scheduler_type,
        num_in_channels=args.num_in_channels,
        upcast_attention=args.upcast_attention,
        from_safetensors=args.from_safetensors,
        device=args.device,
        stable_unclip=args.stable_unclip,
        stable_unclip_prior=args.stable_unclip_prior,
        clip_stats_path=args.clip_stats_path,
        controlnet=args.controlnet,
        vae_path=args.vae_path,
        pipeline_class=pipeline_class,
    )

    if args.half:
        pipe.to(dtype=torch.float16)

    if args.controlnet:
        # only save the controlnet model
        pipe.controlnet.save_pretrained(args.dump_path, safe_serialization=args.to_safetensors)
    else:
        pipe.save_pretrained(args.dump_path, safe_serialization=args.to_safetensors)