File size: 13,109 Bytes
ffead1e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 |
# Script for converting a HF Diffusers saved pipeline to a Stable Diffusion checkpoint.
# *Only* converts the UNet, VAE, and Text Encoder.
# Does not convert optimizer state or any other thing.
import argparse
import os.path as osp
import re
import torch
from safetensors.torch import load_file, save_file
# =================#
# UNet Conversion #
# =================#
unet_conversion_map = [
# (stable-diffusion, HF Diffusers)
("time_embed.0.weight", "time_embedding.linear_1.weight"),
("time_embed.0.bias", "time_embedding.linear_1.bias"),
("time_embed.2.weight", "time_embedding.linear_2.weight"),
("time_embed.2.bias", "time_embedding.linear_2.bias"),
("input_blocks.0.0.weight", "conv_in.weight"),
("input_blocks.0.0.bias", "conv_in.bias"),
("out.0.weight", "conv_norm_out.weight"),
("out.0.bias", "conv_norm_out.bias"),
("out.2.weight", "conv_out.weight"),
("out.2.bias", "conv_out.bias"),
]
unet_conversion_map_resnet = [
# (stable-diffusion, HF Diffusers)
("in_layers.0", "norm1"),
("in_layers.2", "conv1"),
("out_layers.0", "norm2"),
("out_layers.3", "conv2"),
("emb_layers.1", "time_emb_proj"),
("skip_connection", "conv_shortcut"),
]
unet_conversion_map_layer = []
# hardcoded number of downblocks and resnets/attentions...
# would need smarter logic for other networks.
for i in range(4):
# loop over downblocks/upblocks
for j in range(2):
# loop over resnets/attentions for downblocks
hf_down_res_prefix = f"down_blocks.{i}.resnets.{j}."
sd_down_res_prefix = f"input_blocks.{3*i + j + 1}.0."
unet_conversion_map_layer.append((sd_down_res_prefix, hf_down_res_prefix))
if i < 3:
# no attention layers in down_blocks.3
hf_down_atn_prefix = f"down_blocks.{i}.attentions.{j}."
sd_down_atn_prefix = f"input_blocks.{3*i + j + 1}.1."
unet_conversion_map_layer.append((sd_down_atn_prefix, hf_down_atn_prefix))
for j in range(3):
# loop over resnets/attentions for upblocks
hf_up_res_prefix = f"up_blocks.{i}.resnets.{j}."
sd_up_res_prefix = f"output_blocks.{3*i + j}.0."
unet_conversion_map_layer.append((sd_up_res_prefix, hf_up_res_prefix))
if i > 0:
# no attention layers in up_blocks.0
hf_up_atn_prefix = f"up_blocks.{i}.attentions.{j}."
sd_up_atn_prefix = f"output_blocks.{3*i + j}.1."
unet_conversion_map_layer.append((sd_up_atn_prefix, hf_up_atn_prefix))
if i < 3:
# no downsample in down_blocks.3
hf_downsample_prefix = f"down_blocks.{i}.downsamplers.0.conv."
sd_downsample_prefix = f"input_blocks.{3*(i+1)}.0.op."
unet_conversion_map_layer.append((sd_downsample_prefix, hf_downsample_prefix))
# no upsample in up_blocks.3
hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
sd_upsample_prefix = f"output_blocks.{3*i + 2}.{1 if i == 0 else 2}."
unet_conversion_map_layer.append((sd_upsample_prefix, hf_upsample_prefix))
hf_mid_atn_prefix = "mid_block.attentions.0."
sd_mid_atn_prefix = "middle_block.1."
unet_conversion_map_layer.append((sd_mid_atn_prefix, hf_mid_atn_prefix))
for j in range(2):
hf_mid_res_prefix = f"mid_block.resnets.{j}."
sd_mid_res_prefix = f"middle_block.{2*j}."
unet_conversion_map_layer.append((sd_mid_res_prefix, hf_mid_res_prefix))
def convert_unet_state_dict(unet_state_dict):
# buyer beware: this is a *brittle* function,
# and correct output requires that all of these pieces interact in
# the exact order in which I have arranged them.
mapping = {k: k for k in unet_state_dict.keys()}
for sd_name, hf_name in unet_conversion_map:
mapping[hf_name] = sd_name
for k, v in mapping.items():
if "resnets" in k:
for sd_part, hf_part in unet_conversion_map_resnet:
v = v.replace(hf_part, sd_part)
mapping[k] = v
for k, v in mapping.items():
for sd_part, hf_part in unet_conversion_map_layer:
v = v.replace(hf_part, sd_part)
mapping[k] = v
new_state_dict = {v: unet_state_dict[k] for k, v in mapping.items()}
return new_state_dict
# ================#
# VAE Conversion #
# ================#
vae_conversion_map = [
# (stable-diffusion, HF Diffusers)
("nin_shortcut", "conv_shortcut"),
("norm_out", "conv_norm_out"),
("mid.attn_1.", "mid_block.attentions.0."),
]
for i in range(4):
# down_blocks have two resnets
for j in range(2):
hf_down_prefix = f"encoder.down_blocks.{i}.resnets.{j}."
sd_down_prefix = f"encoder.down.{i}.block.{j}."
vae_conversion_map.append((sd_down_prefix, hf_down_prefix))
if i < 3:
hf_downsample_prefix = f"down_blocks.{i}.downsamplers.0."
sd_downsample_prefix = f"down.{i}.downsample."
vae_conversion_map.append((sd_downsample_prefix, hf_downsample_prefix))
hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
sd_upsample_prefix = f"up.{3-i}.upsample."
vae_conversion_map.append((sd_upsample_prefix, hf_upsample_prefix))
# up_blocks have three resnets
# also, up blocks in hf are numbered in reverse from sd
for j in range(3):
hf_up_prefix = f"decoder.up_blocks.{i}.resnets.{j}."
sd_up_prefix = f"decoder.up.{3-i}.block.{j}."
vae_conversion_map.append((sd_up_prefix, hf_up_prefix))
# this part accounts for mid blocks in both the encoder and the decoder
for i in range(2):
hf_mid_res_prefix = f"mid_block.resnets.{i}."
sd_mid_res_prefix = f"mid.block_{i+1}."
vae_conversion_map.append((sd_mid_res_prefix, hf_mid_res_prefix))
vae_conversion_map_attn = [
# (stable-diffusion, HF Diffusers)
("norm.", "group_norm."),
("q.", "query."),
("k.", "key."),
("v.", "value."),
("proj_out.", "proj_attn."),
]
def reshape_weight_for_sd(w):
# convert HF linear weights to SD conv2d weights
return w.reshape(*w.shape, 1, 1)
def convert_vae_state_dict(vae_state_dict):
mapping = {k: k for k in vae_state_dict.keys()}
for k, v in mapping.items():
for sd_part, hf_part in vae_conversion_map:
v = v.replace(hf_part, sd_part)
mapping[k] = v
for k, v in mapping.items():
if "attentions" in k:
for sd_part, hf_part in vae_conversion_map_attn:
v = v.replace(hf_part, sd_part)
mapping[k] = v
new_state_dict = {v: vae_state_dict[k] for k, v in mapping.items()}
weights_to_convert = ["q", "k", "v", "proj_out"]
for k, v in new_state_dict.items():
for weight_name in weights_to_convert:
if f"mid.attn_1.{weight_name}.weight" in k:
print(f"Reshaping {k} for SD format")
new_state_dict[k] = reshape_weight_for_sd(v)
return new_state_dict
# =========================#
# Text Encoder Conversion #
# =========================#
textenc_conversion_lst = [
# (stable-diffusion, HF Diffusers)
("resblocks.", "text_model.encoder.layers."),
("ln_1", "layer_norm1"),
("ln_2", "layer_norm2"),
(".c_fc.", ".fc1."),
(".c_proj.", ".fc2."),
(".attn", ".self_attn"),
("ln_final.", "transformer.text_model.final_layer_norm."),
("token_embedding.weight", "transformer.text_model.embeddings.token_embedding.weight"),
("positional_embedding", "transformer.text_model.embeddings.position_embedding.weight"),
]
protected = {re.escape(x[1]): x[0] for x in textenc_conversion_lst}
textenc_pattern = re.compile("|".join(protected.keys()))
# Ordering is from https://github.com/pytorch/pytorch/blob/master/test/cpp/api/modules.cpp
code2idx = {"q": 0, "k": 1, "v": 2}
def convert_text_enc_state_dict_v20(text_enc_dict):
new_state_dict = {}
capture_qkv_weight = {}
capture_qkv_bias = {}
for k, v in text_enc_dict.items():
if (
k.endswith(".self_attn.q_proj.weight")
or k.endswith(".self_attn.k_proj.weight")
or k.endswith(".self_attn.v_proj.weight")
):
k_pre = k[: -len(".q_proj.weight")]
k_code = k[-len("q_proj.weight")]
if k_pre not in capture_qkv_weight:
capture_qkv_weight[k_pre] = [None, None, None]
capture_qkv_weight[k_pre][code2idx[k_code]] = v
continue
if (
k.endswith(".self_attn.q_proj.bias")
or k.endswith(".self_attn.k_proj.bias")
or k.endswith(".self_attn.v_proj.bias")
):
k_pre = k[: -len(".q_proj.bias")]
k_code = k[-len("q_proj.bias")]
if k_pre not in capture_qkv_bias:
capture_qkv_bias[k_pre] = [None, None, None]
capture_qkv_bias[k_pre][code2idx[k_code]] = v
continue
relabelled_key = textenc_pattern.sub(lambda m: protected[re.escape(m.group(0))], k)
new_state_dict[relabelled_key] = v
for k_pre, tensors in capture_qkv_weight.items():
if None in tensors:
raise Exception("CORRUPTED MODEL: one of the q-k-v values for the text encoder was missing")
relabelled_key = textenc_pattern.sub(lambda m: protected[re.escape(m.group(0))], k_pre)
new_state_dict[relabelled_key + ".in_proj_weight"] = torch.cat(tensors)
for k_pre, tensors in capture_qkv_bias.items():
if None in tensors:
raise Exception("CORRUPTED MODEL: one of the q-k-v values for the text encoder was missing")
relabelled_key = textenc_pattern.sub(lambda m: protected[re.escape(m.group(0))], k_pre)
new_state_dict[relabelled_key + ".in_proj_bias"] = torch.cat(tensors)
return new_state_dict
def convert_text_enc_state_dict(text_enc_dict):
return text_enc_dict
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--model_path", default=None, type=str, required=True, help="Path to the model to convert.")
parser.add_argument("--checkpoint_path", default=None, type=str, required=True, help="Path to the output model.")
parser.add_argument("--half", action="store_true", help="Save weights in half precision.")
parser.add_argument(
"--use_safetensors", action="store_true", help="Save weights use safetensors, default is ckpt."
)
args = parser.parse_args()
assert args.model_path is not None, "Must provide a model path!"
assert args.checkpoint_path is not None, "Must provide a checkpoint path!"
# Path for safetensors
unet_path = osp.join(args.model_path, "unet", "diffusion_pytorch_model.safetensors")
vae_path = osp.join(args.model_path, "vae", "diffusion_pytorch_model.safetensors")
text_enc_path = osp.join(args.model_path, "text_encoder", "model.safetensors")
# Load models from safetensors if it exists, if it doesn't pytorch
if osp.exists(unet_path):
unet_state_dict = load_file(unet_path, device="cpu")
else:
unet_path = osp.join(args.model_path, "unet", "diffusion_pytorch_model.bin")
unet_state_dict = torch.load(unet_path, map_location="cpu")
if osp.exists(vae_path):
vae_state_dict = load_file(vae_path, device="cpu")
else:
vae_path = osp.join(args.model_path, "vae", "diffusion_pytorch_model.bin")
vae_state_dict = torch.load(vae_path, map_location="cpu")
if osp.exists(text_enc_path):
text_enc_dict = load_file(text_enc_path, device="cpu")
else:
text_enc_path = osp.join(args.model_path, "text_encoder", "pytorch_model.bin")
text_enc_dict = torch.load(text_enc_path, map_location="cpu")
# Convert the UNet model
unet_state_dict = convert_unet_state_dict(unet_state_dict)
unet_state_dict = {"model.diffusion_model." + k: v for k, v in unet_state_dict.items()}
# Convert the VAE model
vae_state_dict = convert_vae_state_dict(vae_state_dict)
vae_state_dict = {"first_stage_model." + k: v for k, v in vae_state_dict.items()}
# Easiest way to identify v2.0 model seems to be that the text encoder (OpenCLIP) is deeper
is_v20_model = "text_model.encoder.layers.22.layer_norm2.bias" in text_enc_dict
if is_v20_model:
# Need to add the tag 'transformer' in advance so we can knock it out from the final layer-norm
text_enc_dict = {"transformer." + k: v for k, v in text_enc_dict.items()}
text_enc_dict = convert_text_enc_state_dict_v20(text_enc_dict)
text_enc_dict = {"cond_stage_model.model." + k: v for k, v in text_enc_dict.items()}
else:
text_enc_dict = convert_text_enc_state_dict(text_enc_dict)
text_enc_dict = {"cond_stage_model.transformer." + k: v for k, v in text_enc_dict.items()}
# Put together new checkpoint
state_dict = {**unet_state_dict, **vae_state_dict, **text_enc_dict}
if args.half:
state_dict = {k: v.half() for k, v in state_dict.items()}
if args.use_safetensors:
save_file(state_dict, args.checkpoint_path)
else:
state_dict = {"state_dict": state_dict}
torch.save(state_dict, args.checkpoint_path)
|