File size: 6,372 Bytes
44eca84 1028385 44eca84 f22aece 1028385 44eca84 811a69b 44eca84 1028385 44eca84 1028385 811a69b 1028385 44eca84 1028385 44eca84 1028385 44eca84 1028385 44eca84 1028385 811a69b 1028385 44eca84 1028385 44eca84 1028385 44eca84 1028385 9fb003c 1028385 811a69b 9fb003c 1028385 44eca84 8ad9fee 44eca84 8ad9fee 44eca84 8ad9fee 44eca84 8ad9fee 44eca84 |
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 |
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"source": [
"This Notebook is a Stable-diffusion tool which allows you to find similiar tokens from the SD 1.5 vocab.json that you can use for text-to-image generation"
],
"metadata": {
"id": "L7JTcbOdBPfh"
}
},
{
"cell_type": "code",
"source": [
"# Load the tokens into the colab\n",
"!git clone https://huggingface.co/datasets/codeShare/sd_tokens\n",
"import torch\n",
"from torch import linalg as LA\n",
"device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
"%cd /content/sd_tokens\n",
"token = torch.load('sd15_tensors.pt', map_location=device, weights_only=True)\n",
"#-----#\n",
"\n",
"#Import the vocab.json\n",
"import json\n",
"import pandas as pd\n",
"with open('vocab.json', 'r') as f:\n",
" data = json.load(f)\n",
"\n",
"_df = pd.DataFrame({'count': data})['count']\n",
"\n",
"vocab = {\n",
" value: key for key, value in _df.items()\n",
"}\n",
"#-----#\n",
"\n",
"# Define functions/constants\n",
"NUM_TOKENS = 49407\n",
"\n",
"def absolute_value(x):\n",
" return max(x, -x)\n",
"\n",
"def similarity(id_A , id_B):\n",
" #Tensors\n",
" A = token[id_A]\n",
" B = token[id_B]\n",
" #Tensor vector length (2nd order, i.e (a^2 + b^2 + ....)^(1/2)\n",
" _A = LA.vector_norm(A, ord=2)\n",
" _B = LA.vector_norm(B, ord=2)\n",
" #----#\n",
" result = torch.dot(A,B)/(_A*_B)\n",
" similarity_pcnt = absolute_value(result.item()*100)\n",
" similarity_pcnt_aprox = round(similarity_pcnt, 3)\n",
" result = f'{similarity_pcnt_aprox} %'\n",
" return result\n",
"#----#"
],
"metadata": {
"id": "Ch9puvwKH1s3"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"print(vocab[8922]) #the vocab item for ID 8922\n",
"print(token[8922].shape) #dimension of the token"
],
"metadata": {
"id": "S_Yh9gH_OUA1"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Get the IDs from a prompt text.\n",
"\n",
"The prompt will be enclosed with the <|start-of-text|> and <|end-of-text|> tokens"
],
"metadata": {
"id": "f1-jS7YJApiO"
}
},
{
"cell_type": "code",
"source": [
"\n",
"from transformers import AutoTokenizer\n",
"tokenizer = AutoTokenizer.from_pretrained(\"openai/clip-vit-large-patch14\", clean_up_tokenization_spaces = False)\n",
"prompt= \"banana\" # @param {type:'string'}\n",
"tokenizer_output = tokenizer(text = prompt)\n",
"input_ids = tokenizer_output['input_ids']\n",
"print(input_ids)"
],
"metadata": {
"id": "RPdkYzT2_X85"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#Produce a list id IDs that are most similiar to the prompt ID at positiion 1\n",
"\n",
"id_A = input_ids[1]\n",
"A = token[id_A]\n",
"_A = LA.vector_norm(A, ord=2)\n",
"dots = torch.zeros(NUM_TOKENS)\n",
"\n",
"for index in range(NUM_TOKENS):\n",
" id_B = index\n",
" B = token[id_B]\n",
" _B = LA.vector_norm(B, ord=2)\n",
" result = torch.dot(A,B)/(_A*_B)\n",
" result = absolute_value(result.item())\n",
" dots[index] = result\n",
"\n",
"sorted, indices = torch.sort(dots,dim=0 , descending=True)\n",
"#----#\n",
"print(f'Calculated all cosine-similarities between the token {vocab[id_A]} with ID = {id_A} the rest of the {NUM_TOKENS} tokens as a 1x{sorted.shape[0]} tensor')\n",
"print(f'Calculated indices as a 1x{indices.shape[0]} tensor')"
],
"metadata": {
"id": "juxsvco9B0iV"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"list_size = 100 # @param {type:'number'}\n",
"\n",
"print_ID = False # @param {type:\"boolean\"}\n",
"print_Similarity = True # @param {type:\"boolean\"}\n",
"print_Name = True # @param {type:\"boolean\"}\n",
"print_Divider = False # @param {type:\"boolean\"}\n",
"\n",
"for index in range(list_size):\n",
" id = indices[index].item()\n",
" if (print_Name):\n",
" print(f'{vocab[id]}') # vocab item\n",
" if (print_ID):\n",
" print(f'ID = {id}') # IDs\n",
" if (print_Similarity):\n",
" print(f'similiarity = {round(sorted[index].item()*100,2)} %') # % value\n",
" if (print_Divider):\n",
" print('--------')"
],
"metadata": {
"id": "YIEmLAzbHeuo"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Find the most similiar Tokens for given input"
],
"metadata": {
"id": "qqZ5DvfLBJnw"
}
},
{
"cell_type": "markdown",
"source": [
"Valid ID ranges for id_for_token_A / id_for_token_B are between 0 and 49407"
],
"metadata": {
"id": "kX72bAuhOtlT"
}
},
{
"cell_type": "code",
"source": [
"id_for_token_A = 4567 # @param {type:'number'}\n",
"id_for_token_B = 4343 # @param {type:'number'}\n",
"\n",
"similarity_str = 'The similarity between tokens A and B is ' + similarity(id_for_token_A , id_for_token_B)\n",
"\n",
"print(similarity_str)"
],
"metadata": {
"id": "MwmOdC9cNZty"
},
"execution_count": null,
"outputs": []
}
]
} |