Upload lora_finetune.ipynb

lora_finetune.ipynb

@@ -478,30 +478,6 @@
     "## Train! 🧪"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "733a8ebd-bcc0-4b41-92b4-e95c2e91d363",
-   "metadata": {
-    "id": "733a8ebd-bcc0-4b41-92b4-e95c2e91d363",
-    "pycharm": {
-     "name": "#%% md\n"
-    },
-    "tags": []
-   },
-   "source": [
-    "### `Diffusers` 🧨 Training loop"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "72b2491e-16fe-4b0c-bb50-41db70766c7b",
-   "metadata": {
-    "id": "72b2491e-16fe-4b0c-bb50-41db70766c7b"
-   },
-   "source": [
-    "### Launch training 🚀🚀🚀"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "6dbd7ec5-d4e2-470f-97f2-011a30d04e63",
@@ -509,11 +485,11 @@
     "id": "6dbd7ec5-d4e2-470f-97f2-011a30d04e63"
    },
    "source": [
-    "**Set your LoRA rank**\n",
-    "The rank of your LoRA is linked to its expressiveness.\n",
-    "The bigger the rank the closer we are to regular dreambooth, and in theory we have more expressive power (and heavier weights).\n",
+    "**Adjust your LoRA rank**\n",
+    "\n",
+    "The rank determines how expressive your LoRA will be. Higher ranks bring it closer to standard DreamBooth, offering more expressive capabilities but also increasing the model’s size.\n",
     "\n",
-    "For a very simple concept that you have a good high quality image set for (e.g. a pet, a generic object), a rank as low as 4 can be enough to get great results. We reccomend going between 8 and 64 depending on your concept and how much of a priortiy it is for you to keep the LoRA small or not.  "
+    "A recommend rank is between 8 and 64 based on your concept and your priority to balance expressiveness with a smaller LoRA size."
    ]
   },
   {
@@ -535,7 +511,7 @@
    "id": "78325966",
    "metadata": {},
    "source": [
-    "Before you start free some memory:"
+    "Free some memory if needed"
    ]
   },
   {