File size: 8,296 Bytes
d6e21f3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# SDXL with Custom LoRA on T4 GPU\n",
"\n",
"This notebook sets up Stable Diffusion XL (SDXL) on a T4 GPU in Google Colab with Python 3.11, downloads the base model from Hugging Face, and applies a custom LoRA model from Hugging Face or Civitai. It generates images using the configured pipeline.\n",
"\n",
"**Prerequisites:**\n",
"- Hugging Face account and token for gated model access (e.g., `stabilityai/stable-diffusion-xl-base-1.0`).\n",
"- Civitai API key if downloading LoRA from Civitai.\n",
"- Ensure Colab is set to T4 GPU (Runtime > Change runtime type > T4 GPU).\n",
"\n",
"**Note:** Replace placeholders (e.g., `YOUR_HF_TOKEN`, `YOUR_CIVITAI_API_KEY`) with your actual credentials."
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"# Install dependencies for Python 3.11\n",
"!pip install torch==2.2.0 torchvision==0.17.0 --index-url https://download.pytorch.org/whl/cu118\n",
"!pip install diffusers==0.29.2 transformers==4.44.2 accelerate==0.33.0 safetensors==0.4.5\n",
"!pip install requests\n",
"\n",
"# Verify Python version\n",
"import sys\n",
"print(sys.version)\n",
"\n",
"# Check GPU availability\n",
"import torch\n",
"print(f\"CUDA Available: {torch.cuda.is_available()}\")\n",
"print(f\"GPU: {torch.cuda.get_device_name(0) if torch.cuda.is_available() else 'No GPU'}\")"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 1: Authenticate and Download Models\n",
"Authenticate with Hugging Face to download the SDXL base model. Optionally, provide a Civitai API key for LoRA download."
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"from huggingface_hub import login\n",
"import os\n",
"\n",
"# Log in to Hugging Face\n",
"HF_TOKEN = \"YOUR_HF_TOKEN\" # Replace with your Hugging Face token\n",
"login(HF_TOKEN)\n",
"\n",
"# Set Civitai API key (if downloading from Civitai)\n",
"CIVITAI_API_KEY = \"YOUR_CIVITAI_API_KEY\" # Replace with your Civitai API key or set to None\n",
"os.environ[\"CIVITAI_API_KEY\"] = CIVITAI_API_KEY if CIVITAI_API_KEY else \"\"\n",
"\n",
"# Download SDXL base model\n",
"from diffusers import StableDiffusionXLPipeline\n",
"base_model = \"stabilityai/stable-diffusion-xl-base-1.0\"\n",
"pipeline = StableDiffusionXLPipeline.from_pretrained(\n",
" base_model,\n",
" torch_dtype=torch.float16,\n",
" variant=\"fp16\",\n",
" use_safetensors=True\n",
").to(\"cuda\")"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 2: Download Custom LoRA\n",
"Choose to download a LoRA model from Hugging Face or Civitai. Replace the URLs/IDs with your desired LoRA model."
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"import requests\n",
"import os\n",
"\n",
"def download_hf_lora(repo_id, filename, local_dir=\"./lora\"):\n",
" os.makedirs(local_dir, exist_ok=True)\n",
" local_path = os.path.join(local_dir, filename)\n",
" url = f\"https://huggingface.co/{repo_id}/resolve/main/{filename}\"\n",
" headers = {\"Authorization\": f\"Bearer {HF_TOKEN}\"}\n",
" response = requests.get(url, headers=headers)\n",
" response.raise_for_status()\n",
" with open(local_path, \"wb\") as f:\n",
" f.write(response.content)\n",
" return local_path\n",
"\n",
"def download_civitai_lora(model_id, filename, local_dir=\"./lora\"):\n",
" os.makedirs(local_dir, exist_ok=True)\n",
" local_path = os.path.join(local_dir, filename)\n",
" url = f\"https://civitai.com/api/download/models/{model_id}\"\n",
" headers = {\"Authorization\": f\"Bearer {os.environ['CIVITAI_API_KEY']}\"}\n",
" response = requests.get(url, headers=headers)\n",
" response.raise_for_status()\n",
" with open(local_path, \"wb\") as f:\n",
" f.write(response.content)\n",
" return local_path\n",
"\n",
"# Example: Download LoRA (choose one method)\n",
"# Hugging Face LoRA (e.g., a hypothetical LoRA model)\n",
"lora_path = download_hf_lora(\n",
" repo_id=\"username/sdxl-lora-model\", # Replace with actual Hugging Face repo ID\n",
" filename=\"model.safetensors\" # Replace with actual filename\n",
")\n",
"\n",
"# Civitai LoRA (uncomment to use)\n",
"# lora_path = download_civitai_lora(\n",
"# model_id=\"123456\", # Replace with Civitai model ID\n",
"# filename=\"lora_model.safetensors\"\n",
"# )"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 3: Load LoRA into Pipeline\n",
"Load the custom LoRA weights into the SDXL pipeline."
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"# Load LoRA weights\n",
"pipeline.load_lora_weights(\n",
" lora_path,\n",
" adapter_name=\"custom_lora\"\n",
")\n",
"\n",
"# Enable LoRA\n",
"pipeline.set_adapters([\"custom_lora\"], adapter_weights=[1.0])\n",
"\n",
"# Optimize for T4 GPU\n",
"pipeline.enable_model_cpu_offload()\n",
"pipeline.enable_vae_slicing()"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 4: Generate Images\n",
"Configure the prompt and generate images using the SDXL pipeline with LoRA."
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"prompt = \"A futuristic cityscape at sunset, cyberpunk style, highly detailed, vibrant colors\"\n",
"negative_prompt = \"blurry, low quality, artifacts\"\n",
"\n",
"images = pipeline(\n",
" prompt=prompt,\n",
" negative_prompt=negative_prompt,\n",
" num_inference_steps=30,\n",
" guidance_scale=7.5,\n",
" height=1024,\n",
" width=1024,\n",
" num_images_per_prompt=1\n",
").images\n",
"\n",
"# Save and display the image\n",
"images[0].save(\"output.png\")\n",
"images[0]"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Notes\n",
"- **T4 GPU Optimization**: The notebook uses `float16` precision, VAE slicing, and model CPU offloading to fit within T4 GPU memory constraints (16GB VRAM).\n",
"- **LoRA Model**: Ensure the LoRA model is compatible with SDXL. Replace placeholder repo IDs or model IDs with actual values from Hugging Face or Civitai.\n",
"- **Performance**: Adjust `num_inference_steps` and `guidance_scale` for quality vs. speed trade-offs.\n",
"- **Storage**: Generated images are saved as `output.png` in the Colab environment. Download them manually if needed."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.11.0"
}
},
"nbformat": 4,
"nbformat_minor": 4
} |