Spaces:
Runtime error
Runtime error
File size: 3,678 Bytes
6ed1db6 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.chdir(\"..\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"from diffusers.pipelines import FluxPipeline\n",
"from src.condition import Condition\n",
"from PIL import Image\n",
"\n",
"from src.generate import generate, seed_everything"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pipe = FluxPipeline.from_pretrained(\n",
" \"black-forest-labs/FLUX.1-dev\", torch_dtype=torch.bfloat16\n",
")\n",
"pipe = pipe.to(\"cuda\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pipe.load_lora_weights(\n",
" \"Yuanshi/OminiControl\",\n",
" weight_name=f\"experimental/fill.safetensors\",\n",
" adapter_name=\"fill\",\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"image = Image.open(\"assets/monalisa.jpg\").convert(\"RGB\").resize((512, 512))\n",
"\n",
"masked_image = image.copy()\n",
"masked_image.paste((0, 0, 0), (128, 100, 384, 220))\n",
"\n",
"condition = Condition(\"fill\", masked_image)\n",
"\n",
"seed_everything()\n",
"result_img = generate(\n",
" pipe,\n",
" prompt=\"The Mona Lisa is wearing a white VR headset with 'Omini' written on it.\",\n",
" conditions=[condition],\n",
").images[0]\n",
"\n",
"concat_image = Image.new(\"RGB\", (1536, 512))\n",
"concat_image.paste(image, (0, 0))\n",
"concat_image.paste(condition.condition, (512, 0))\n",
"concat_image.paste(result_img, (1024, 0))\n",
"concat_image"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"image = Image.open(\"assets/book.jpg\").convert(\"RGB\").resize((512, 512))\n",
"\n",
"w, h, min_dim = image.size + (min(image.size),)\n",
"image = image.crop(\n",
" ((w - min_dim) // 2, (h - min_dim) // 2, (w + min_dim) // 2, (h + min_dim) // 2)\n",
").resize((512, 512))\n",
"\n",
"\n",
"masked_image = image.copy()\n",
"masked_image.paste((0, 0, 0), (150, 150, 350, 250))\n",
"masked_image.paste((0, 0, 0), (200, 380, 320, 420))\n",
"\n",
"condition = Condition(\"fill\", masked_image)\n",
"\n",
"seed_everything()\n",
"result_img = generate(\n",
" pipe,\n",
" prompt=\"A yellow book with the word 'OMINI' in large font on the cover. The text 'for FLUX' appears at the bottom.\",\n",
" conditions=[condition],\n",
").images[0]\n",
"\n",
"concat_image = Image.new(\"RGB\", (1536, 512))\n",
"concat_image.paste(image, (0, 0))\n",
"concat_image.paste(condition.condition, (512, 0))\n",
"concat_image.paste(result_img, (1024, 0))\n",
"concat_image"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.12.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|