File size: 9,472 Bytes
c16e8a4 8592059 c16e8a4 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "c15deb04-94a0-4073-a174-adcd22af10b8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"✅ Создана новая модель: <class 'diffusers.models.autoencoders.autoencoder_asym_kl.AsymmetricAutoencoderKL'>\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"The config attributes {'block_out_channels': [128, 256, 512, 512, 512], 'force_upcast': False} were passed to AsymmetricAutoencoderKL, but are not expected and will be ignored. Please verify your config.json configuration file.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"--- Перенос весов ---\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 248/248 [00:00<00:00, 142199.23it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"✅ Перенос завершён.\n",
"Статистика:\n",
" перенесено: 142\n",
" дублировано: 26\n",
" сдвинуто: 106\n",
" пропущено: 0\n",
"\n",
"Неперенесённые ключи (первые 20):\n",
" decoder.condition_encoder.layers.0.weight\n",
" decoder.condition_encoder.layers.0.bias\n",
" decoder.condition_encoder.layers.1.weight\n",
" decoder.condition_encoder.layers.1.bias\n",
" decoder.condition_encoder.layers.2.weight\n",
" decoder.condition_encoder.layers.2.bias\n",
" decoder.condition_encoder.layers.3.weight\n",
" decoder.condition_encoder.layers.3.bias\n",
" decoder.condition_encoder.layers.4.weight\n",
" decoder.condition_encoder.layers.4.bias\n"
]
}
],
"source": [
"from diffusers.models import AsymmetricAutoencoderKL, AutoencoderKL\n",
"import torch\n",
"from tqdm import tqdm\n",
"\n",
"# ---- Конфиг новой модели ----\n",
"config = {\n",
" \"_class_name\": \"AsymmetricAutoencoderKL\",\n",
" \"act_fn\": \"silu\",\n",
" \"in_channels\": 3,\n",
" \"out_channels\": 3,\n",
" \"scaling_factor\": 1.0,\n",
" \"norm_num_groups\": 32,\n",
" \"down_block_out_channels\": [128, 256, 512, 512],\n",
" \"down_block_types\": [\n",
" \"DownEncoderBlock2D\",\n",
" \"DownEncoderBlock2D\",\n",
" \"DownEncoderBlock2D\",\n",
" \"DownEncoderBlock2D\",\n",
" ],\n",
" \"latent_channels\": 16,\n",
" \"up_block_out_channels\": [64, 128, 256, 512, 512], # +1 блок\n",
" \"up_block_types\": [\n",
" \"UpDecoderBlock2D\",\n",
" \"UpDecoderBlock2D\",\n",
" \"UpDecoderBlock2D\",\n",
" \"UpDecoderBlock2D\",\n",
" \"UpDecoderBlock2D\",\n",
" ],\n",
"}\n",
"\n",
"# ---- Создание пустой асимметричной модели ----\n",
"vae = AsymmetricAutoencoderKL(\n",
" act_fn=config[\"act_fn\"],\n",
" down_block_out_channels=config[\"down_block_out_channels\"],\n",
" down_block_types=config[\"down_block_types\"],\n",
" latent_channels=config[\"latent_channels\"],\n",
" up_block_out_channels=config[\"up_block_out_channels\"],\n",
" up_block_types=config[\"up_block_types\"],\n",
" in_channels=config[\"in_channels\"],\n",
" out_channels=config[\"out_channels\"],\n",
" scaling_factor=config[\"scaling_factor\"],\n",
" norm_num_groups=config[\"norm_num_groups\"],\n",
" layers_per_down_block=2,\n",
" layers_per_up_block = 2,\n",
" sample_size = 1024\n",
")\n",
"\n",
"vae.save_pretrained(\"asymmetric_vae_empty\")\n",
"print(\"✅ Создана новая модель:\", type(vae))\n",
"\n",
"# ---- Функция переноса весов ----\n",
"def transfer_weights_with_duplication(old_path, new_path, save_path=\"asymmetric_vae\", device=\"cuda\", dtype=torch.float16):\n",
" old_vae = AutoencoderKL.from_pretrained(old_path,subfolder=\"vae\").to(device, dtype=dtype)\n",
" new_vae = AsymmetricAutoencoderKL.from_pretrained(new_path).to(device, dtype=dtype)\n",
"\n",
" old_sd = old_vae.state_dict()\n",
" new_sd = new_vae.state_dict()\n",
"\n",
" transferred_keys = set()\n",
" transfer_stats = {\"перенесено\": 0, \"дублировано\": 0, \"сдвинуто\": 0, \"пропущено\": 0}\n",
"\n",
" print(\"\\n--- Перенос весов ---\")\n",
"\n",
" for k, v in tqdm(old_sd.items()):\n",
" # === Копирование энкодера ===\n",
" if \"encoder\" in k or \"quant_conv\" in k or \"post_quant_conv\" in k:\n",
" if k in new_sd and new_sd[k].shape == v.shape:\n",
" new_sd[k] = v.clone()\n",
" transferred_keys.add(k)\n",
" transfer_stats[\"перенесено\"] += 1\n",
" continue\n",
"\n",
" # === Перенос декодера ===\n",
" if \"decoder.up_blocks\" in k:\n",
" parts = k.split(\".\")\n",
" idx = int(parts[2])\n",
"\n",
" # сдвигаем индекс на +1 (так как добавлен новый блок в начало)\n",
" new_idx = idx + 1\n",
" new_k = \".\".join([parts[0], parts[1], str(new_idx)] + parts[3:])\n",
" if new_k in new_sd and new_sd[new_k].shape == v.shape:\n",
" new_sd[new_k] = v.clone()\n",
" transferred_keys.add(new_k)\n",
" transfer_stats[\"сдвинуто\"] += 1\n",
" continue\n",
"\n",
" # === Перенос прочих совпадающих ключей ===\n",
" if k in new_sd and new_sd[k].shape == v.shape:\n",
" new_sd[k] = v.clone()\n",
" transferred_keys.add(k)\n",
" transfer_stats[\"перенесено\"] += 1\n",
"\n",
" # === Дублирование весов старого 512→512 блока в новый ===\n",
" ref_prefix = \"decoder.up_blocks.1\" # старый первый up-блок (512→512)\n",
" new_prefix = \"decoder.up_blocks.0\" # новый добавленный блок\n",
" for k, v in old_sd.items():\n",
" if k.startswith(ref_prefix):\n",
" new_k = k.replace(ref_prefix, new_prefix)\n",
" if new_k in new_sd and new_sd[new_k].shape == v.shape:\n",
" new_sd[new_k] = v.clone()\n",
" transferred_keys.add(new_k)\n",
" transfer_stats[\"дублировано\"] += 1\n",
"\n",
" # === Загрузка и сохранение ===\n",
" new_vae.load_state_dict(new_sd, strict=False)\n",
" new_vae.save_pretrained(save_path)\n",
"\n",
" print(\"\\n✅ Перенос завершён.\")\n",
" print(\"Статистика:\")\n",
" for k, v in transfer_stats.items():\n",
" print(f\" {k}: {v}\")\n",
"\n",
" missing = [k for k in new_sd.keys() if k not in transferred_keys]\n",
" if missing:\n",
" print(\"\\nНеперенесённые ключи (первые 20):\")\n",
" for k in missing[:20]:\n",
" print(\" \", k)\n",
"\n",
"# ---- Запуск ----\n",
"transfer_weights_with_duplication(\"AiArtLab/simplevae\", \"asymmetric_vae_empty\", save_path=\"vae\")\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "65653a65-e7c2-4b67-bc17-62c21cfd1db8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting hf_transfer\n",
" Downloading hf_transfer-0.1.9-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.7 kB)\n",
"Downloading hf_transfer-0.1.9-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m34.5 MB/s\u001b[0m \u001b[33m0:00:00\u001b[0m\n",
"\u001b[?25hInstalling collected packages: hf_transfer\n",
"Successfully installed hf_transfer-0.1.9\n"
]
}
],
"source": [
"!pip install hf_transfer"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "59fcafb9-6d89-49b4-8362-b4891f591687",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|