Upload folder using huggingface_hub

AnimatedDiff_Colab.ipynb

@@ -0,0 +1,826 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "t0gCc4zNO0-J",
+        "outputId": "cb8cfaad-d4f1-4c26-92a6-644eb1bc9039"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Requirement already satisfied: wandb in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (0.16.0)\n",
+            "Requirement already satisfied: Click!=8.0.0,>=7.1 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (8.1.7)\n",
+            "Requirement already satisfied: GitPython!=3.1.29,>=1.0.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (3.1.40)\n",
+            "Requirement already satisfied: requests<3,>=2.0.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (2.31.0)\n",
+            "Requirement already satisfied: psutil>=5.0.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (5.9.5)\n",
+            "Requirement already satisfied: sentry-sdk>=1.0.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (1.35.0)\n",
+            "Requirement already satisfied: docker-pycreds>=0.4.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (0.4.0)\n",
+            "Requirement already satisfied: PyYAML in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (6.0.1)\n",
+            "Requirement already satisfied: setproctitle in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (1.3.3)\n",
+            "Requirement already satisfied: setuptools in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (68.2.2)\n",
+            "Requirement already satisfied: appdirs>=1.4.3 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (1.4.4)\n",
+            "Requirement already satisfied: protobuf!=4.21.0,<5,>=3.19.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from wandb) (4.25.0)\n",
+            "Requirement already satisfied: colorama in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from Click!=8.0.0,>=7.1->wandb) (0.4.6)\n",
+            "Requirement already satisfied: six>=1.4.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from docker-pycreds>=0.4.0->wandb) (1.16.0)\n",
+            "Requirement already satisfied: gitdb<5,>=4.0.1 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from GitPython!=3.1.29,>=1.0.0->wandb) (4.0.11)\n",
+            "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from requests<3,>=2.0.0->wandb) (3.3.2)\n",
+            "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from requests<3,>=2.0.0->wandb) (3.4)\n",
+            "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from requests<3,>=2.0.0->wandb) (2.1.0)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from requests<3,>=2.0.0->wandb) (2023.7.22)\n",
+            "Requirement already satisfied: smmap<6,>=3.0.1 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from gitdb<5,>=4.0.1->GitPython!=3.1.29,>=1.0.0->wandb) (5.0.1)\n"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "wandb: ERROR Find detailed error logs at: C:\\Users\\texas\\AppData\\Local\\Temp\\debug-cli.texas.log\n",
+            "Error: api_key not configured (no-tty). call wandb login [your_api_key]\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install wandb\n",
+        "!wandb login"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "UGH2QZ4tDlzw",
+        "outputId": "0e2339d0-78b3-4a23-eddf-589c805adcc8"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.19.4)\n",
+            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (3.13.1)\n",
+            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2023.6.0)\n",
+            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2.31.0)\n",
+            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.66.1)\n",
+            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (6.0.1)\n",
+            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.5.0)\n",
+            "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (23.2)\n",
+            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.3.2)\n",
+            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.4)\n",
+            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2.0.7)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2023.7.22)\n",
+            "\n",
+            "    _|    _|  _|    _|    _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|_|_|_|    _|_|      _|_|_|  _|_|_|_|\n",
+            "    _|    _|  _|    _|  _|        _|          _|    _|_|    _|  _|            _|        _|    _|  _|        _|\n",
+            "    _|_|_|_|  _|    _|  _|  _|_|  _|  _|_|    _|    _|  _|  _|  _|  _|_|      _|_|_|    _|_|_|_|  _|        _|_|_|\n",
+            "    _|    _|  _|    _|  _|    _|  _|    _|    _|    _|    _|_|  _|    _|      _|        _|    _|  _|        _|\n",
+            "    _|    _|    _|_|      _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|        _|    _|    _|_|_|  _|_|_|_|\n",
+            "\n",
+            "    To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .\n",
+            "Token: \n",
+            "Add token as git credential? (Y/n) Y\n",
+            "Token is valid (permission: write).\n",
+            "\u001b[1m\u001b[31mCannot authenticate through git-credential as no helper is defined on your machine.\n",
+            "You might have to re-authenticate when pushing to the Hugging Face Hub.\n",
+            "Run the following command in your terminal in case you want to set the 'store' credential helper as default.\n",
+            "\n",
+            "git config --global credential.helper store\n",
+            "\n",
+            "Read https://git-scm.com/book/en/v2/Git-Tools-Credential-Storage for more details.\u001b[0m\n",
+            "Token has not been saved to git credential helper.\n",
+            "Your token has been saved to /root/.cache/huggingface/token\n",
+            "Login successful\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install huggingface_hub\n",
+        "# You already have it if you installed transformers or datasets\n",
+        "\n",
+        "!huggingface-cli login"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 1000
+        },
+        "id": "iPDlxLC9PFzV",
+        "outputId": "076dead2-d2da-42bf-a867-1a0d59e0b3c2"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Requirement already satisfied: einops in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (0.7.0)\n",
+            "Requirement already satisfied: omegaconf in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (2.3.0)\n",
+            "Requirement already satisfied: decord in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (0.6.0)\n",
+            "Requirement already satisfied: safetensors in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (0.4.0)\n",
+            "Requirement already satisfied: diffusers==0.11.1 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from diffusers[torch]==0.11.1) (0.11.1)\n",
+            "Requirement already satisfied: transformers in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (4.25.1)\n",
+            "Requirement already satisfied: xformers in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (0.0.16)\n",
+            "Requirement already satisfied: triton==2.0.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (2.0.0)\n",
+            "Collecting mediapy\n",
+            "  Downloading mediapy-1.1.9-py3-none-any.whl.metadata (4.8 kB)\n",
+            "Requirement already satisfied: imageio[pyav] in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (2.27.0)\n",
+            "Requirement already satisfied: importlib-metadata in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from diffusers==0.11.1->diffusers[torch]==0.11.1) (6.8.0)\n",
+            "Requirement already satisfied: filelock in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from diffusers==0.11.1->diffusers[torch]==0.11.1) (3.13.1)\n",
+            "Requirement already satisfied: huggingface-hub>=0.10.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from diffusers==0.11.1->diffusers[torch]==0.11.1) (0.19.4)\n",
+            "Requirement already satisfied: numpy in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from diffusers==0.11.1->diffusers[torch]==0.11.1) (1.26.0)\n",
+            "Requirement already satisfied: regex!=2019.12.17 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from diffusers==0.11.1->diffusers[torch]==0.11.1) (2023.10.3)\n",
+            "Requirement already satisfied: requests in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from diffusers==0.11.1->diffusers[torch]==0.11.1) (2.31.0)\n",
+            "Requirement already satisfied: Pillow in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from diffusers==0.11.1->diffusers[torch]==0.11.1) (10.1.0)\n",
+            "Requirement already satisfied: cmake in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from triton==2.0.0) (3.27.7)\n",
+            "Requirement already satisfied: torch in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from triton==2.0.0) (1.13.1)\n",
+            "Collecting accelerate>=0.11.0 (from diffusers[torch]==0.11.1)\n",
+            "  Downloading accelerate-0.24.1-py3-none-any.whl.metadata (18 kB)\n",
+            "Requirement already satisfied: antlr4-python3-runtime==4.9.* in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from omegaconf) (4.9.3)\n",
+            "Requirement already satisfied: PyYAML>=5.1.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from omegaconf) (6.0.1)\n",
+            "Requirement already satisfied: packaging>=20.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from transformers) (23.2)\n",
+            "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from transformers) (0.13.3)\n",
+            "Requirement already satisfied: tqdm>=4.27 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from transformers) (4.66.1)\n",
+            "Requirement already satisfied: pyre-extensions==0.0.23 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from xformers) (0.0.23)\n",
+            "Requirement already satisfied: typing-inspect in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from pyre-extensions==0.0.23->xformers) (0.9.0)\n",
+            "Requirement already satisfied: typing-extensions in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from pyre-extensions==0.0.23->xformers) (4.8.0)\n",
+            "Collecting av (from imageio[pyav])\n",
+            "  Downloading av-11.0.0-cp310-cp310-win_amd64.whl.metadata (4.7 kB)\n",
+            "Requirement already satisfied: ipython in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from mediapy) (8.17.2)\n",
+            "Requirement already satisfied: matplotlib in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from mediapy) (3.8.1)\n",
+            "Requirement already satisfied: psutil in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from accelerate>=0.11.0->diffusers[torch]==0.11.1) (5.9.5)\n",
+            "Requirement already satisfied: fsspec>=2023.5.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from huggingface-hub>=0.10.0->diffusers==0.11.1->diffusers[torch]==0.11.1) (2023.10.0)\n",
+            "Requirement already satisfied: colorama in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from tqdm>=4.27->transformers) (0.4.6)\n",
+            "Requirement already satisfied: zipp>=0.5 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from importlib-metadata->diffusers==0.11.1->diffusers[torch]==0.11.1) (3.17.0)\n",
+            "Requirement already satisfied: decorator in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from ipython->mediapy) (5.1.1)\n",
+            "Requirement already satisfied: jedi>=0.16 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from ipython->mediapy) (0.19.1)\n",
+            "Requirement already satisfied: matplotlib-inline in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from ipython->mediapy) (0.1.6)\n",
+            "Requirement already satisfied: prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from ipython->mediapy) (3.0.41)\n",
+            "Requirement already satisfied: pygments>=2.4.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from ipython->mediapy) (2.16.1)\n",
+            "Requirement already satisfied: stack-data in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from ipython->mediapy) (0.6.2)\n",
+            "Requirement already satisfied: traitlets>=5 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from ipython->mediapy) (5.13.0)\n",
+            "Requirement already satisfied: exceptiongroup in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from ipython->mediapy) (1.1.3)\n",
+            "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from matplotlib->mediapy) (1.2.0)\n",
+            "Requirement already satisfied: cycler>=0.10 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from matplotlib->mediapy) (0.12.1)\n",
+            "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from matplotlib->mediapy) (4.44.3)\n",
+            "Requirement already satisfied: kiwisolver>=1.3.1 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from matplotlib->mediapy) (1.4.5)\n",
+            "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from matplotlib->mediapy) (3.1.1)\n",
+            "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from matplotlib->mediapy) (2.8.2)\n",
+            "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from requests->diffusers==0.11.1->diffusers[torch]==0.11.1) (3.3.2)\n",
+            "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from requests->diffusers==0.11.1->diffusers[torch]==0.11.1) (3.4)\n",
+            "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from requests->diffusers==0.11.1->diffusers[torch]==0.11.1) (2.1.0)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from requests->diffusers==0.11.1->diffusers[torch]==0.11.1) (2023.7.22)\n",
+            "Requirement already satisfied: parso<0.9.0,>=0.8.3 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from jedi>=0.16->ipython->mediapy) (0.8.3)\n",
+            "Requirement already satisfied: wcwidth in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30->ipython->mediapy) (0.2.10)\n",
+            "Requirement already satisfied: six>=1.5 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from python-dateutil>=2.7->matplotlib->mediapy) (1.16.0)\n",
+            "Requirement already satisfied: executing>=1.2.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from stack-data->ipython->mediapy) (2.0.1)\n",
+            "Requirement already satisfied: asttokens>=2.1.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from stack-data->ipython->mediapy) (2.4.1)\n",
+            "Requirement already satisfied: pure-eval in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from stack-data->ipython->mediapy) (0.2.2)\n",
+            "Requirement already satisfied: mypy-extensions>=0.3.0 in c:\\users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages (from typing-inspect->pyre-extensions==0.0.23->xformers) (1.0.0)\n",
+            "Downloading mediapy-1.1.9-py3-none-any.whl (25 kB)\n",
+            "Downloading accelerate-0.24.1-py3-none-any.whl (261 kB)\n",
+            "   ---------------------------------------- 0.0/261.4 kB ? eta -:--:--\n",
+            "   -------------- ------------------------- 92.2/261.4 kB 2.6 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  256.0/261.4 kB 4.0 MB/s eta 0:00:01\n",
+            "   ---------------------------------------- 261.4/261.4 kB 2.7 MB/s eta 0:00:00\n",
+            "Downloading av-11.0.0-cp310-cp310-win_amd64.whl (25.9 MB)\n",
+            "   ---------------------------------------- 0.0/25.9 MB ? eta -:--:--\n",
+            "    --------------------------------------- 0.6/25.9 MB 12.0 MB/s eta 0:00:03\n",
+            "   -- ------------------------------------- 1.5/25.9 MB 11.9 MB/s eta 0:00:03\n",
+            "   --- ------------------------------------ 2.0/25.9 MB 11.7 MB/s eta 0:00:03\n",
+            "   --- ------------------------------------ 2.2/25.9 MB 9.5 MB/s eta 0:00:03\n",
+            "   ---- ----------------------------------- 3.0/25.9 MB 10.8 MB/s eta 0:00:03\n",
+            "   ----- ---------------------------------- 3.5/25.9 MB 11.1 MB/s eta 0:00:03\n",
+            "   ------ --------------------------------- 4.2/25.9 MB 11.2 MB/s eta 0:00:02\n",
+            "   ------ --------------------------------- 4.3/25.9 MB 11.4 MB/s eta 0:00:02\n",
+            "   -------- ------------------------------- 5.4/25.9 MB 11.4 MB/s eta 0:00:02\n",
+            "   --------- ------------------------------ 5.9/25.9 MB 11.5 MB/s eta 0:00:02\n",
+            "   ---------- ----------------------------- 6.6/25.9 MB 11.6 MB/s eta 0:00:02\n",
+            "   ---------- ----------------------------- 7.1/25.9 MB 11.7 MB/s eta 0:00:02\n",
+            "   ----------- ---------------------------- 7.7/25.9 MB 11.7 MB/s eta 0:00:02\n",
+            "   ------------ --------------------------- 8.3/25.9 MB 11.8 MB/s eta 0:00:02\n",
+            "   ------------- -------------------------- 8.8/25.9 MB 11.8 MB/s eta 0:00:02\n",
+            "   -------------- ------------------------- 9.5/25.9 MB 11.9 MB/s eta 0:00:02\n",
+            "   --------------- ------------------------ 10.3/25.9 MB 11.9 MB/s eta 0:00:02\n",
+            "   ---------------- ----------------------- 10.9/25.9 MB 12.4 MB/s eta 0:00:02\n",
+            "   ----------------- ---------------------- 11.5/25.9 MB 12.1 MB/s eta 0:00:02\n",
+            "   ------------------ --------------------- 12.1/25.9 MB 12.1 MB/s eta 0:00:02\n",
+            "   ------------------- -------------------- 12.5/25.9 MB 12.8 MB/s eta 0:00:02\n",
+            "   ------------------- -------------------- 12.9/25.9 MB 12.1 MB/s eta 0:00:02\n",
+            "   ------------------- -------------------- 12.9/25.9 MB 11.5 MB/s eta 0:00:02\n",
+            "   --------------------- ------------------ 13.7/25.9 MB 11.3 MB/s eta 0:00:02\n",
+            "   --------------------- ------------------ 14.1/25.9 MB 11.1 MB/s eta 0:00:02\n",
+            "   ---------------------- ----------------- 14.5/25.9 MB 11.9 MB/s eta 0:00:01\n",
+            "   ----------------------- ---------------- 15.0/25.9 MB 11.3 MB/s eta 0:00:01\n",
+            "   ----------------------- ---------------- 15.3/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ------------------------ --------------- 15.8/25.9 MB 10.7 MB/s eta 0:00:01\n",
+            "   ------------------------ --------------- 16.1/25.9 MB 10.6 MB/s eta 0:00:01\n",
+            "   ------------------------- -------------- 16.6/25.9 MB 10.4 MB/s eta 0:00:01\n",
+            "   -------------------------- ------------- 17.0/25.9 MB 10.2 MB/s eta 0:00:01\n",
+            "   -------------------------- ------------- 17.4/25.9 MB 10.1 MB/s eta 0:00:01\n",
+            "   --------------------------- ------------ 18.0/25.9 MB 9.9 MB/s eta 0:00:01\n",
+            "   ---------------------------- ----------- 18.6/25.9 MB 9.9 MB/s eta 0:00:01\n",
+            "   ----------------------------- ---------- 19.1/25.9 MB 9.9 MB/s eta 0:00:01\n",
+            "   ------------------------------ --------- 19.7/25.9 MB 9.9 MB/s eta 0:00:01\n",
+            "   ------------------------------- -------- 20.3/25.9 MB 9.9 MB/s eta 0:00:01\n",
+            "   -------------------------------- ------- 20.9/25.9 MB 9.9 MB/s eta 0:00:01\n",
+            "   --------------------------------- ------ 21.4/25.9 MB 9.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------- ----- 22.0/25.9 MB 9.8 MB/s eta 0:00:01\n",
+            "   ---------------------------------- ----- 22.5/25.9 MB 9.8 MB/s eta 0:00:01\n",
+            "   ----------------------------------- ---- 23.1/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ------------------------------------ --- 23.8/25.9 MB 10.7 MB/s eta 0:00:01\n",
+            "   ------------------------------------- -- 24.3/25.9 MB 10.7 MB/s eta 0:00:01\n",
+            "   -------------------------------------- - 24.9/25.9 MB 11.1 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.3/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 11.1 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------  25.9/25.9 MB 10.9 MB/s eta 0:00:01\n",
+            "   ---------------------------------------- 25.9/25.9 MB 3.9 MB/s eta 0:00:00\n",
+            "Installing collected packages: av, accelerate, mediapy\n",
+            "Successfully installed accelerate-0.24.1 av-11.0.0 mediapy-1.1.9\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install einops omegaconf decord safetensors diffusers[torch]==0.11.1 transformers xformers triton==2.0.0 imageio[pyav] mediapy"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "metadata": {
+        "id": "0jsTnJgXVjC6"
+      },
+      "outputs": [],
+      "source": [
+        "# !pip install -U \"jax[cuda12_pip]\" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ePPaNOhFZFgH",
+        "outputId": "e116c509-8495-4c8b-edda-a47d8754c462"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "The following additional packages will be installed:\n",
+            "  libaria2-0 libc-ares2\n",
+            "The following NEW packages will be installed:\n",
+            "  aria2 libaria2-0 libc-ares2\n",
+            "0 upgraded, 3 newly installed, 0 to remove and 10 not upgraded.\n",
+            "Need to get 1,513 kB of archives.\n",
+            "After this operation, 5,441 kB of additional disk space will be used.\n",
+            "Selecting previously unselected package libc-ares2:amd64.\n",
+            "(Reading database ... 120880 files and directories currently installed.)\n",
+            "Preparing to unpack .../libc-ares2_1.18.1-1ubuntu0.22.04.2_amd64.deb ...\n",
+            "Unpacking libc-ares2:amd64 (1.18.1-1ubuntu0.22.04.2) ...\n",
+            "Selecting previously unselected package libaria2-0:amd64.\n",
+            "Preparing to unpack .../libaria2-0_1.36.0-1_amd64.deb ...\n",
+            "Unpacking libaria2-0:amd64 (1.36.0-1) ...\n",
+            "Selecting previously unselected package aria2.\n",
+            "Preparing to unpack .../aria2_1.36.0-1_amd64.deb ...\n",
+            "Unpacking aria2 (1.36.0-1) ...\n",
+            "Setting up libc-ares2:amd64 (1.18.1-1ubuntu0.22.04.2) ...\n",
+            "Setting up libaria2-0:amd64 (1.36.0-1) ...\n",
+            "Setting up aria2 (1.36.0-1) ...\n",
+            "Processing triggers for man-db (2.10.2-1) ...\n",
+            "Processing triggers for libc-bin (2.35-0ubuntu3.4) ...\n",
+            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_0.so.3 is not a symbolic link\n",
+            "\n",
+            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc.so.2 is not a symbolic link\n",
+            "\n",
+            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_5.so.3 is not a symbolic link\n",
+            "\n",
+            "/sbin/ldconfig.real: /usr/local/lib/libtbb.so.12 is not a symbolic link\n",
+            "\n",
+            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc_proxy.so.2 is not a symbolic link\n",
+            "\n",
+            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind.so.3 is not a symbolic link\n",
+            "\n",
+            "\u001b[0m\n",
+            "Download Results:\n",
+            "gid   |stat|avg speed  |path/URI\n",
+            "======+====+===========+=======================================================\n",
+            "401ea6|\u001b[1;32mOK\u001b[0m  |   168MiB/s|/content/AnimateDiff-SceneFusion/models/DreamBooth_LoRA/toonyou_beta3.safetensors\n",
+            "\n",
+            "Status Legend:\n",
+            "(OK):download completed.\n"
+          ]
+        }
+      ],
+      "source": [
+        "!apt -y install -qq aria2\n",
+        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/camenduru/AnimateDiff/resolve/main/toonyou_beta3.safetensors -d /content/AnimateDiff-SceneFusion/models/DreamBooth_LoRA -o toonyou_beta3.safetensors"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "jXBHQRi1LKnb",
+        "outputId": "10219ae9-e50d-4a31-fa6f-37f8cccc1fb3"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Collecting ffmpeg\n",
+            "  Downloading ffmpeg-1.4.tar.gz (5.1 kB)\n",
+            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+            "Building wheels for collected packages: ffmpeg\n",
+            "  Building wheel for ffmpeg (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+            "  Created wheel for ffmpeg: filename=ffmpeg-1.4-py3-none-any.whl size=6082 sha256=289c2192632ef676cb1b88a59f16c39dd96bd8cf3a7c2cf8f661d5b4d0481c1d\n",
+            "  Stored in directory: /root/.cache/pip/wheels/8e/7a/69/cd6aeb83b126a7f04cbe7c9d929028dc52a6e7d525ff56003a\n",
+            "Successfully built ffmpeg\n",
+            "Installing collected packages: ffmpeg\n",
+            "Successfully installed ffmpeg-1.4\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install ffmpeg"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Hdx9PUJXG-d_",
+        "outputId": "c102aafb-7572-447c-bf13-84709c21c65d"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "/content/AnimateDiff-SceneFusion\n"
+          ]
+        }
+      ],
+      "source": [
+        "%cd AnimateDiff-SceneFusion\n",
+        "# !pip install -r requirements.txt"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "n581MT-dIxAh",
+        "outputId": "5bf3af95-bec0-4888-b983-aebb2d7efd32"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "Cloning into 'models/StableDiffusion'...\n",
+            "Updating files:  47% (8/17)\n",
+            "Updating files:  52% (9/17)\n",
+            "Updating files:  58% (10/17)\n",
+            "Updating files:  64% (11/17)\n",
+            "Updating files:  70% (12/17)\n",
+            "Updating files:  76% (13/17)\n",
+            "Updating files:  82% (14/17)\n",
+            "Updating files:  88% (15/17)\n",
+            "Updating files:  94% (16/17)\n",
+            "Updating files: 100% (17/17)\n",
+            "Updating files: 100% (17/17), done.\n",
+            "Filtering content:  50% (2/4), 394.42 MiB | 17.74 MiB/s\n",
+            "Filtering content:  50% (2/4), 974.35 MiB | 10.32 MiB/s\n",
+            "Filtering content:  75% (3/4), 974.35 MiB | 10.32 MiB/s\n",
+            "Filtering content:  75% (3/4), 2.55 GiB | 6.73 MiB/s   \n",
+            "Filtering content: 100% (4/4), 2.55 GiB | 6.73 MiB/s\n",
+            "Filtering content: 100% (4/4), 2.55 GiB | 5.89 MiB/s, done.\n"
+          ]
+        }
+      ],
+      "source": [
+        "# %cd /content/AnimateDiff-SceneFusion\n",
+        "\n",
+        "# import huggingface_hub\n",
+        "\n",
+        "# files = [\"config.json\", \"diffusion_pytorch_model.bin\", \"diffusion_pytorch_model.fp16.bin\", \"diffusion_pytorch_model.fp16.safetensors\", \"diffusion_pytorch_model.non_ema.bin\", \"diffusion_pytorch_model.non_ema.safetensors\", \"diffusion_pytorch_model.safetensors\"]\n",
+        "\n",
+        "# for file in files:\n",
+        "#     huggingface_hub.hf_hub_download(\"runwayml/stable-diffusion-v1-5\", file, subfolder=\"unet\", local_dir=\"unet\")\n",
+        "\n",
+        "\n",
+        "!git clone -b fp16 https://huggingface.co/runwayml/stable-diffusion-v1-5 models/StableDiffusion/"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "RLuAKqD3I2pv",
+        "outputId": "37bccf0c-bb76-4d0e-e668-f91254d4f3a3"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Access denied with the following error:\n",
+            "Access denied with the following error:\n"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            " \tToo many users have viewed or downloaded this file recently. Please\n",
+            "\ttry accessing the file again later. If the file you are trying to\n",
+            "\taccess is particularly large or is shared with many people, it may\n",
+            "\ttake up to 24 hours to be able to view or download the file. If you\n",
+            "\tstill can't access a file after 24 hours, contact your domain\n",
+            "\tadministrator. \n",
+            "\n",
+            "You may still be able to access the file from the browser:\n",
+            "\n",
+            "\t https://drive.google.com/uc?id=1RqkQuGPaCO5sGZ6V6KZ-jUWmsRu48Kdq \n",
+            "\n",
+            "\n",
+            " \tToo many users have viewed or downloaded this file recently. Please\n",
+            "\ttry accessing the file again later. If the file you are trying to\n",
+            "\taccess is particularly large or is shared with many people, it may\n",
+            "\ttake up to 24 hours to be able to view or download the file. If you\n",
+            "\tstill can't access a file after 24 hours, contact your domain\n",
+            "\tadministrator. \n",
+            "\n",
+            "You may still be able to access the file from the browser:\n",
+            "\n",
+            "\t https://drive.google.com/uc?id=1ql0g_Ys4UCz2RnokYlBjyOYPbttbIpbu \n",
+            "\n"
+          ]
+        }
+      ],
+      "source": [
+        "# %cd AnimateDiff-SceneFusion\n",
+        "!bash download_bashscripts/0-MotionModule.sh"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
+      "metadata": {
+        "id": "1VUbuB4M2UhZ"
+      },
+      "outputs": [],
+      "source": [
+        "%load_ext autoreload\n",
+        "%autoreload 2"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "metadata": {
+        "cellView": "form",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "VZ-CXYNhKXuy",
+        "outputId": "88d9be57-67dc-4c4b-a6cc-b39623118d2a"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "[*] Weights will be saved at models/Motion_Module/test\n"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "The syntax of the command is incorrect.\n"
+          ]
+        }
+      ],
+      "source": [
+        "# @title TRAINING CONFIG\n",
+        "# %cd /content/AnimateDiff-SceneFusion\n",
+        "\n",
+        "# @markdown ## Config\n",
+        "\n",
+        "PROJECT = \"test\" # @param{\"type\":\"string\"}\n",
+        "\n",
+        "OUTPUT_DIR = \"models/Motion_Module/%s\" % PROJECT\n",
+        "\n",
+        "print(f\"[*] Weights will be saved at {OUTPUT_DIR}\")\n",
+        "\n",
+        "!mkdir -p $OUTPUT_DIR\n",
+        "\n",
+        "# @markdown ## Model\n",
+        "\n",
+        "MODEL_NAME = \"models/StableDiffusion/\" # @param{\"type\":\"string\"}\n",
+        "\n",
+        "# @markdown ## Train\n",
+        "\n",
+        "CONFIG_NAME = f\"configs/{PROJECT}.yaml\" #@param {type:\"string\"}\n",
+        "MOTION_MODULE_NAME=\"models/Motion_Module/mm_sd_v15.ckpt\" #@param{\"type\":\"string\"}\n",
+        "\n",
+        "train_video_folder = f\"data/output\" #@param {type:\"string\"}\n",
+        "train_csv_path = f\"data/output.csv\" #@param {type:\"string\"}\n",
+        "train_prompt = \"camera panning right to left, a bird's eye view of a row of buildings in a city with trees in the foreground, masterpiece, best quality\" #@param {type:\"string\"}\n",
+        "video_length = 5 #@param {type:\"number\"}\n",
+        "sample_size = 256 #@param {type:\"number\"}\n",
+        "learning_rate = 3e-4 #@param {type:\"number\"}\n",
+        "train_steps = 1 #@param {type:\"number\"}\n",
+        "validation_steps = 1 #@param {type:\"number\"}\n",
+        "\n",
+        "\n",
+        "# @markdown ## Infer\n",
+        "LORA_DREAMBOOTH_PATH=\"models/DreamBooth_LoRA/toonyou_beta3.safetensors\" #@param{\"type\":\"string\"}\n",
+        "\n",
+        "\n",
+        "from omegaconf import OmegaConf\n",
+        "\n",
+        "\n",
+        "config = {\n",
+        "  \"pretrained_model_path\": \"models/StableDiffusion/\",\n",
+        "  \"motion_module\": MOTION_MODULE_NAME,\n",
+        "  \"output_dir\": OUTPUT_DIR,\n",
+        "  \"train_data\": {\n",
+        "    \"video_folder\": train_video_folder,\n",
+        "    \"csv_path\": train_csv_path,\n",
+        "    \"sample_n_frames\": video_length,\n",
+        "    \"sample_stride\": 100,\n",
+        "    \"sample_size\": sample_size\n",
+        "  },\n",
+        "  \"validation_data\": {\n",
+        "    \"prompts\": [\n",
+        "      f\"{train_prompt}\",\n",
+        "    ],\n",
+        "    \"video_length\": video_length,\n",
+        "    \"width\": sample_size,\n",
+        "    \"height\": sample_size,\n",
+        "    \"num_inference_steps\": 20,\n",
+        "    \"guidance_scale\": 12.5,\n",
+        "    \"temporal_context\": 24,\n",
+        "    \"use_inv_latent\": True,\n",
+        "    \"num_inv_steps\": 50,\n",
+        "  },\n",
+        "  \"learning_rate\": learning_rate,\n",
+        "  \"train_batch_size\": 1,\n",
+        "  \"max_train_steps\": train_steps,\n",
+        "  \"checkpointing_steps\": 100,\n",
+        "  \"validation_steps\": validation_steps,\n",
+        "  \"trainable_modules\": [\n",
+        "    \"to_q\",\n",
+        "  ],\n",
+        "  \"seed\": 33,\n",
+        "  \"mixed_precision\": \"fp16\",\n",
+        "  \"use_8bit_adam\": False,\n",
+        "  \"gradient_checkpointing\": True,\n",
+        "  \"enable_xformers_memory_efficient_attention\": True,\n",
+        "}\n",
+        "\n",
+        "OmegaConf.save(config, CONFIG_NAME)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "kpUetphRI9D3",
+        "outputId": "d0bba9b2-b93c-476a-9909-94e9f7d5239b"
+      },
+      "outputs": [],
+      "source": [
+        "# %cd /content/AnimateDiff-SceneFusion\n",
+        "# !python -m torch.distributed.run --nnodes=1 --nproc_per_node=1 train.py --config configs/training/training.yaml\n",
+        "\n",
+        "# !accelerate launch train.py --config=configs/training/training.yaml\n",
+        "!accelerate launch  train.py --config=configs/{PROJECT}.yaml --python={3.10}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 365
+        },
+        "id": "IZ2U776S06Gn",
+        "outputId": "bae1ea5f-55e6-4a20-8b53-7c641b4ebba5"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "c:\\Users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+            "  from .autonotebook import tqdm as notebook_tqdm\n"
+          ]
+        },
+        {
+          "ename": "OSError",
+          "evalue": "Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory models/StableDiffusion/.",
+          "output_type": "error",
+          "traceback": [
+            "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+            "\u001b[1;31mOSError\u001b[0m                                   Traceback (most recent call last)",
+            "\u001b[1;32mc:\\Users\\texas\\Desktop\\School\\SceneFusion\\AnimateDiff-SceneFusion\\AnimatedDiff_Colab.ipynb Cell 13\u001b[0m line \u001b[0;36m2\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/texas/Desktop/School/SceneFusion/AnimateDiff-SceneFusion/AnimatedDiff_Colab.ipynb#X20sZmlsZQ%3D%3D?line=24'>25</a>\u001b[0m \u001b[39m### >>> create validation pipeline >>> ###\u001b[39;00m\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/texas/Desktop/School/SceneFusion/AnimateDiff-SceneFusion/AnimatedDiff_Colab.ipynb#X20sZmlsZQ%3D%3D?line=25'>26</a>\u001b[0m tokenizer    \u001b[39m=\u001b[39m CLIPTokenizer\u001b[39m.\u001b[39mfrom_pretrained(model_path, subfolder\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mtokenizer\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m---> <a href='vscode-notebook-cell:/c%3A/Users/texas/Desktop/School/SceneFusion/AnimateDiff-SceneFusion/AnimatedDiff_Colab.ipynb#X20sZmlsZQ%3D%3D?line=26'>27</a>\u001b[0m text_encoder \u001b[39m=\u001b[39m CLIPTextModel\u001b[39m.\u001b[39;49mfrom_pretrained(model_path, subfolder\u001b[39m=\u001b[39;49m\u001b[39m\"\u001b[39;49m\u001b[39mtext_encoder\u001b[39;49m\u001b[39m\"\u001b[39;49m)\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/texas/Desktop/School/SceneFusion/AnimateDiff-SceneFusion/AnimatedDiff_Colab.ipynb#X20sZmlsZQ%3D%3D?line=27'>28</a>\u001b[0m vae          \u001b[39m=\u001b[39m AutoencoderKL\u001b[39m.\u001b[39mfrom_pretrained(model_path, subfolder\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mvae\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/texas/Desktop/School/SceneFusion/AnimateDiff-SceneFusion/AnimatedDiff_Colab.ipynb#X20sZmlsZQ%3D%3D?line=28'>29</a>\u001b[0m unet         \u001b[39m=\u001b[39m UNet3DConditionModel\u001b[39m.\u001b[39mfrom_pretrained_2d(model_path, subfolder\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39munet\u001b[39m\u001b[39m\"\u001b[39m, unet_additional_kwargs\u001b[39m=\u001b[39mOmegaConf\u001b[39m.\u001b[39mto_container(inference_config\u001b[39m.\u001b[39munet_additional_kwargs))\n",
+            "File \u001b[1;32mc:\\Users\\texas\\anaconda3\\envs\\animatediff\\lib\\site-packages\\transformers\\modeling_utils.py:2093\u001b[0m, in \u001b[0;36mPreTrainedModel.from_pretrained\u001b[1;34m(cls, pretrained_model_name_or_path, *model_args, **kwargs)\u001b[0m\n\u001b[0;32m   2087\u001b[0m         \u001b[39mraise\u001b[39;00m \u001b[39mEnvironmentError\u001b[39;00m(\n\u001b[0;32m   2088\u001b[0m             \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mError no file named \u001b[39m\u001b[39m{\u001b[39;00mWEIGHTS_NAME\u001b[39m}\u001b[39;00m\u001b[39m found in directory \u001b[39m\u001b[39m{\u001b[39;00mpretrained_model_name_or_path\u001b[39m}\u001b[39;00m\u001b[39m but \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   2089\u001b[0m             \u001b[39m\"\u001b[39m\u001b[39mthere is a file for Flax weights. Use `from_flax=True` to load this model from those \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   2090\u001b[0m             \u001b[39m\"\u001b[39m\u001b[39mweights.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   2091\u001b[0m         )\n\u001b[0;32m   2092\u001b[0m     \u001b[39melse\u001b[39;00m:\n\u001b[1;32m-> 2093\u001b[0m         \u001b[39mraise\u001b[39;00m \u001b[39mEnvironmentError\u001b[39;00m(\n\u001b[0;32m   2094\u001b[0m             \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mError no file named \u001b[39m\u001b[39m{\u001b[39;00mWEIGHTS_NAME\u001b[39m}\u001b[39;00m\u001b[39m, \u001b[39m\u001b[39m{\u001b[39;00mTF2_WEIGHTS_NAME\u001b[39m}\u001b[39;00m\u001b[39m, \u001b[39m\u001b[39m{\u001b[39;00mTF_WEIGHTS_NAME\u001b[39m \u001b[39m\u001b[39m+\u001b[39m\u001b[39m \u001b[39m\u001b[39m'\u001b[39m\u001b[39m.index\u001b[39m\u001b[39m'\u001b[39m\u001b[39m}\u001b[39;00m\u001b[39m or \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   2095\u001b[0m             \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m{\u001b[39;00mFLAX_WEIGHTS_NAME\u001b[39m}\u001b[39;00m\u001b[39m found in directory \u001b[39m\u001b[39m{\u001b[39;00mpretrained_model_name_or_path\u001b[39m}\u001b[39;00m\u001b[39m.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   2096\u001b[0m         )\n\u001b[0;32m   2097\u001b[0m \u001b[39melif\u001b[39;00m os\u001b[39m.\u001b[39mpath\u001b[39m.\u001b[39misfile(os\u001b[39m.\u001b[39mpath\u001b[39m.\u001b[39mjoin(subfolder, pretrained_model_name_or_path)):\n\u001b[0;32m   2098\u001b[0m     archive_file \u001b[39m=\u001b[39m pretrained_model_name_or_path\n",
+            "\u001b[1;31mOSError\u001b[0m: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory models/StableDiffusion/."
+          ]
+        }
+      ],
+      "source": [
+        "# %cd /content/AnimateDiff-SceneFusion\n",
+        "\n",
+        "from animatediff.pipelines.pipeline_animation import AnimationPipeline\n",
+        "from diffusers import AutoencoderKL, DDPMScheduler, DDIMScheduler\n",
+        "from transformers import CLIPTextModel, CLIPTokenizer\n",
+        "from omegaconf import OmegaConf\n",
+        "from animatediff.models.unet import UNet3DConditionModel\n",
+        "from animatediff.pipelines.pipeline_animation import AnimationPipeline\n",
+        "from animatediff.utils.util import save_videos_grid\n",
+        "from animatediff.utils.util import load_weights\n",
+        "from diffusers.utils.import_utils import is_xformers_available\n",
+        "from typing import Any\n",
+        "import torch\n",
+        "from einops import rearrange\n",
+        "import torchvision\n",
+        "\n",
+        "import numpy as np\n",
+        "\n",
+        "\n",
+        "model_path = \"models/StableDiffusion/\"\n",
+        "inference_config_path = \"configs/inference/inference-v3.yaml\"\n",
+        "motion_module = \"models/Motion_Module/mm_sd_v15.ckpt\"\n",
+        "\n",
+        "inference_config = OmegaConf.load(inference_config_path)\n",
+        "### >>> create validation pipeline >>> ###\n",
+        "tokenizer    = CLIPTokenizer.from_pretrained(model_path, subfolder=\"tokenizer\")\n",
+        "text_encoder = CLIPTextModel.from_pretrained(model_path, subfolder=\"text_encoder\")\n",
+        "vae          = AutoencoderKL.from_pretrained(model_path, subfolder=\"vae\")\n",
+        "unet         = UNet3DConditionModel.from_pretrained_2d(model_path, subfolder=\"unet\", unet_additional_kwargs=OmegaConf.to_container(inference_config.unet_additional_kwargs))\n",
+        "\n",
+        "if is_xformers_available(): unet.enable_xformers_memory_efficient_attention()\n",
+        "else: assert False\n",
+        "\n",
+        "pipeline = AnimationPipeline(\n",
+        "    vae=vae, text_encoder=text_encoder, tokenizer=tokenizer, unet=unet,\n",
+        "    scheduler=DDIMScheduler(**OmegaConf.to_container(inference_config.noise_scheduler_kwargs.DDIMScheduler)),\n",
+        ").to(\"cuda\")\n",
+        "\n",
+        "pipeline = load_weights(\n",
+        "    pipeline,\n",
+        "    # motion module\n",
+        "    motion_module_path         = motion_module,\n",
+        "    motion_module_lora_configs = [],\n",
+        "    # image layers\n",
+        "    dreambooth_model_path      = \"\",\n",
+        "    lora_model_path            = \"\",\n",
+        "    lora_alpha                 = 0.8,\n",
+        ").to(\"cuda\")\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {
+        "id": "VnDjPeeq1Sdx"
+      },
+      "outputs": [],
+      "source": [
+        "pipeline.save_config(\"./\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "nzn0gZA8F4Pk"
+      },
+      "outputs": [],
+      "source": [
+        "# prompt: save model to huggingface repo\n",
+        "\n",
+        "!git lfs install\n",
+        "# !git clone https://huggingface.co/bluestarburst/AnimateDiff-SceneFusion /content/huggingface\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "H_OhGJrCPjYb"
+      },
+      "outputs": [],
+      "source": [
+        "!cp /content/AnimateDiff-SceneFusion/animatediff/pipelines/pipeline_animation.py /content/AnimateDiff-SceneFusion/pipeline.py"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "qvK9PwJlSUCg"
+      },
+      "outputs": [],
+      "source": [
+        "%cd /content/\n",
+        "!huggingface-cli upload AnimateDiff-SceneFusion"
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "gpuType": "T4",
+      "machine_shape": "hm",
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "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": "3.10.13"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

animatediff/models/attention.py

@@ -11,7 +11,8 @@ from diffusers.configuration_utils import ConfigMixin, register_to_config
 from diffusers import ModelMixin
 from diffusers.utils import BaseOutput
 from diffusers.utils.import_utils import is_xformers_available
-from diffusers.models.attention import CrossAttention, FeedForward, AdaLayerNorm
+from diffusers.models.attention import Attention as CrossAttention, FeedForward, AdaLayerNorm
+from typing import Any, Callable, Dict, List, Optional, Union
 
 from einops import rearrange, repeat
 import pdb
@@ -225,7 +226,7 @@ class BasicTransformerBlock(nn.Module):
             nn.init.zeros_(self.attn_temp.to_out[0].weight.data)
             self.norm_temp = AdaLayerNorm(dim, num_embeds_ada_norm) if self.use_ada_layer_norm else nn.LayerNorm(dim)
 
-    def set_use_memory_efficient_attention_xformers(self, use_memory_efficient_attention_xformers: bool):
+    def set_use_memory_efficient_attention_xformers(self, use_memory_efficient_attention_xformers: bool, attention_op: Optional[Callable] = None):
         if not is_xformers_available():
             print("Here is how to install it")
             raise ModuleNotFoundError(

animatediff/models/motion_module.py

@@ -11,7 +11,7 @@ from diffusers.configuration_utils import ConfigMixin, register_to_config
 from diffusers import ModelMixin
 from diffusers.utils import BaseOutput
 from diffusers.utils.import_utils import is_xformers_available
-from diffusers.models.attention import CrossAttention, FeedForward
+from diffusers.models.attention import Attention as CrossAttention, FeedForward
 
 from einops import rearrange, repeat
 import math

animatediff/pipelines/pipeline_animation.py

@@ -425,4 +425,4 @@ class AnimationPipeline(DiffusionPipeline):
         if not return_dict:
             return video
 
-        return AnimationPipelineOutput(videos=video)
+        return AnimationPipelineOutput(videos=video)        

configs/test.yaml

@@ -1,6 +1,6 @@
-pretrained_model_path: /content/AnimateDiff-SceneFusion/models/StableDiffusion/
-motion_module: /content/AnimateDiff-SceneFusion/models/Motion_Module/mm_sd_v15.ckpt
-output_dir: /content/AnimateDiff-SceneFusion/models/Motion_Module/test
+pretrained_model_path: models/StableDiffusion/
+motion_module: models/Motion_Module/mm_sd_v15.ckpt
+output_dir: models/Motion_Module/test
 train_data:
   video_folder: data/output
   csv_path: data/output.csv

handler.py

@@ -48,18 +48,6 @@ class EndpointHandler():
             lora_model_path            = "",
             lora_alpha                 = 0.8,
         ).to("cuda")
-
-    def initialize(self, context):
-        """
-        Initialize model. This will be called during model loading time
-        """
-        
-        
-
-    def preprocess(self, data):
-        """
-        preprocess will be called once for each request.
-        """
     
     def __call__(self, prompt, negative_prompt, steps, guidance_scale):
         """

models/Motion_Module/test/config.yaml

@@ -1,5 +1,5 @@
-pretrained_model_path: /content/AnimateDiff-SceneFusion/models/StableDiffusion/
-output_dir: /content/AnimateDiff-SceneFusion/models/Motion_Module/test
+pretrained_model_path: models/StableDiffusion/
+output_dir: models/Motion_Module/test
 train_data:
   video_folder: data/output
   csv_path: data/output.csv
@@ -42,7 +42,7 @@ mixed_precision: fp16
 use_8bit_adam: false
 enable_xformers_memory_efficient_attention: true
 seed: 33
-motion_module: /content/AnimateDiff-SceneFusion/models/Motion_Module/mm_sd_v15.ckpt
+motion_module: models/Motion_Module/mm_sd_v15.ckpt
 inference_config_path: configs/inference/inference-v3.yaml
 motion_module_pe_multiplier: 1
 dataset_class: MultiTuneAVideoDataset

models/StableDiffusion/.gitattributes

@@ -32,4 +32,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 v1-5-pruned-emaonly.ckpt filter=lfs diff=lfs merge=lfs -text
-v1-5-pruned.ckpt filter=lfs diff=lfs merge=lfs -text

models/StableDiffusion/README.md

@@ -4,17 +4,18 @@ tags:
 - stable-diffusion
 - stable-diffusion-diffusers
 - text-to-image
-inference: true
+inference: false
 extra_gated_prompt: |-
   This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
-  The CreativeML OpenRAIL License specifies: 
-
   1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content 
   2. CompVis claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
   3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
-  Please read the full license carefully here: https://huggingface.co/spaces/CompVis/stable-diffusion-license
-      
-extra_gated_heading: Please read the LICENSE to access this model
+  Please read the full license here: https://huggingface.co/spaces/CompVis/stable-diffusion-license
+  
+  By clicking on "Access repository" below, you accept that your *contact information* (email address and username) can be shared with the model authors as well.
+    
+extra_gated_fields:
+ I have read the License and agree with its terms: checkbox
 ---
 
 # Stable Diffusion v1-5 Model Card
@@ -30,11 +31,10 @@ You can use this both with the [🧨Diffusers library](https://github.com/huggin
 ### Diffusers
 ```py
 from diffusers import StableDiffusionPipeline
-import torch
 
 model_id = "runwayml/stable-diffusion-v1-5"
-pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
-pipe = pipe.to("cuda")
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16, revision="fp16")
+pipe = pipe.to(device)
 
 prompt = "a photo of an astronaut riding a horse on mars"
 image = pipe(prompt).images[0]  
@@ -45,10 +45,7 @@ For more detailed instructions, use-cases and examples in JAX follow the instruc
 
 ### Original GitHub Repository
 
-1. Download the weights 
-   - [v1-5-pruned-emaonly.ckpt](https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt) - 4.27GB, ema-only weight. uses less VRAM - suitable for inference
-   - [v1-5-pruned.ckpt](https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned.ckpt) - 7.7GB, ema+non-ema weights. uses more VRAM - suitable for fine-tuning
-
+1. Download the weights [v1-5-pruned-emaonly.ckpt](https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt)
 2. Follow instructions [here](https://github.com/runwayml/stable-diffusion).
 
 ## Model Details
@@ -147,23 +144,22 @@ The model developers used the following dataset for training the model:
 - LAION-2B (en) and subsets thereof (see next section)
 
 **Training Procedure**
-Stable Diffusion v1-5 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training, 
+Stable Diffusion v1-4 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training, 
 
 - Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
 - Text prompts are encoded through a ViT-L/14 text-encoder.
 - The non-pooled output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross-attention.
 - The loss is a reconstruction objective between the noise that was added to the latent and the prediction made by the UNet.
 
-Currently six Stable Diffusion checkpoints are provided, which were trained as follows.
+We currently provide four checkpoints, which were trained as follows.
 - [`stable-diffusion-v1-1`](https://huggingface.co/CompVis/stable-diffusion-v1-1): 237,000 steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en).
   194,000 steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`).
 - [`stable-diffusion-v1-2`](https://huggingface.co/CompVis/stable-diffusion-v1-2): Resumed from `stable-diffusion-v1-1`.
   515,000 steps at resolution `512x512` on "laion-improved-aesthetics" (a subset of laion2B-en,
 filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the LAION-5B metadata, the aesthetics score is estimated using an [improved aesthetics estimator](https://github.com/christophschuhmann/improved-aesthetic-predictor)).
-- [`stable-diffusion-v1-3`](https://huggingface.co/CompVis/stable-diffusion-v1-3): Resumed from `stable-diffusion-v1-2` - 195,000 steps at resolution `512x512` on "laion-improved-aesthetics" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
-- [`stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) Resumed from `stable-diffusion-v1-2` - 225,000 steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
-- [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) Resumed from `stable-diffusion-v1-2` - 595,000 steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
-- [`stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting) Resumed from `stable-diffusion-v1-5` - then 440,000 steps of inpainting training at resolution 512x512 on “laion-aesthetics v2 5+” and 10% dropping of the text-conditioning. For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, we generate synthetic masks and in 25% mask everything.
+- [`stable-diffusion-v1-3`](https://huggingface.co/CompVis/stable-diffusion-v1-3): Resumed from `stable-diffusion-v1-2`. 195,000 steps at resolution `512x512` on "laion-improved-aesthetics" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
+- [`stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) Resumed from `stable-diffusion-v1-2`.225,000 steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
+- [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) Resumed from `stable-diffusion-v1-2` 595,000 steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
 
 - **Hardware:** 32 x 8 x A100 GPUs
 - **Optimizer:** AdamW

models/StableDiffusion/model_index.json

@@ -3,7 +3,7 @@
   "_diffusers_version": "0.6.0",
   "feature_extractor": [
     "transformers",
-    "CLIPImageProcessor"
+    "CLIPFeatureExtractor"
   ],
   "safety_checker": [
     "stable_diffusion",

models/StableDiffusion/safety_checker/config.json

@@ -1,6 +1,6 @@
 {
-  "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
-  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
+  "_commit_hash": null,
+  "_name_or_path": "/home/patrick/stable-diffusion-v1-5/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -88,7 +88,7 @@
     "num_attention_heads": 12,
     "num_hidden_layers": 12
   },
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": null,
   "vision_config": {
     "_name_or_path": "",

models/StableDiffusion/scheduler/scheduler_config.json

@@ -10,4 +10,4 @@
   "steps_offset": 1,
   "trained_betas": null,
   "clip_sample": false
-}
+}

models/StableDiffusion/text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "/home/patrick/stable-diffusion-v1-5/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.22.0.dev0",
   "vocab_size": 49408
 }

models/StableDiffusion/tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "openai/clip-vit-large-patch14",
+  "name_or_path": "/home/patrick/stable-diffusion-v1-5/tokenizer",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

models/StableDiffusion/unet/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.6.0",
+  "_name_or_path": "/home/patrick/stable-diffusion-v1-5/unet",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [

models/StableDiffusion/vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.6.0",
+  "_name_or_path": "/home/patrick/stable-diffusion-v1-5/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -19,7 +20,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
+  "sample_size": 256,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

tuneavideo/models/attention.py

@@ -11,7 +11,8 @@ from diffusers.configuration_utils import ConfigMixin, register_to_config
 from diffusers.modeling_utils import ModelMixin
 from diffusers.utils import BaseOutput
 from diffusers.utils.import_utils import is_xformers_available
-from diffusers.models.attention import CrossAttention, FeedForward, AdaLayerNorm
+from diffusers.models.attention import Attention as CrossAttention, FeedForward, AdaLayerNorm
+from typing import Any, Callable, Dict, List, Optional, Union
 
 from einops import rearrange, repeat
 
@@ -201,7 +202,7 @@ class BasicTransformerBlock(nn.Module):
         nn.init.zeros_(self.attn_temp.to_out[0].weight.data)
         self.norm_temp = AdaLayerNorm(dim, num_embeds_ada_norm) if self.use_ada_layer_norm else nn.LayerNorm(dim)
 
-    def set_use_memory_efficient_attention_xformers(self, use_memory_efficient_attention_xformers: bool):
+    def set_use_memory_efficient_attention_xformers(self, use_memory_efficient_attention_xformers: bool, attention_op: Optional[Callable] = None):
         if not is_xformers_available():
             print("Here is how to install it")
             raise ModuleNotFoundError(