{
 "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
}