garystafford

import os

# project configuration
project_name = "mb_amg_gt_oue_dreambooth"
model_name_base = "stabilityai/stable-diffusion-xl-base-1.0"
model_name_refiner = "stabilityai/stable-diffusion-xl-refiner-1.0"

# fine-tuning prompts
# 'oue' is a rare tokens, 'car' is a class
instance_prompt = "photo of oue car"

garystafford

%%sh

export PIP_ROOT_USER_ACTION=ignore

pip install -Uq pip # optional
pip install -Uq autotrain-advanced
pip install -q ipywidgets==7.8.1

garystafford

from diffusers import DiffusionPipeline, StableDiffusionXLImg2ImgPipeline

device = "cuda" # cpu or cuda

pipeline = DiffusionPipeline.from_pretrained(
    model_name_base,
    torch_dtype=torch.float16,
).to(device)

refiner = StableDiffusionXLImg2ImgPipeline.from_pretrained(

garystafford

# optional descriptive terms: sleek, futuristic, metallic, colorful, urban
subject_prompt = """oue, marker rendering of oue electric scooter, concept art, 
futuristic cityscape, solid color background, bright vibrant colors, marker, sketch, 
illustration, illustrative, marker drawing, expressive strokes, graphic"""

subject_negative_prompt = """person, people, human, rider, floating objects, text, 
words, writing, letters, phrases, trademark, watermark, icon, logo, banner, signature, 
username, monochrome, cropped, cut-off, patterned background"""

refiner_prompt = """sharp, crisp, in-focus, uncropped, high-quality"""

garystafford

chpt  paras    words     chrs   tokens    ratio     cost
--------------------------------------------------------
   1     39    5,547   30,624    7,218     4.24    0.080
   2     62    5,305   28,510    6,833     4.17    0.075
   3     46    5,571   29,805    7,075     4.21    0.078
   4     86    5,703   30,267    7,338     4.12    0.081
   5     28    3,390   18,019    4,650     3.88    0.051
   6     64    5,299   29,195    7,524     3.88    0.083
   7     62    5,424   29,964    7,120     4.21    0.078
   8     59    6,044   32,637    7,970     4.09    0.088

garystafford

garystafford

# Purpose: Generate demographic data
# Author: Gary A. Stafford and GitHub Copilot
# Date: 2023-04-14
# Usage: python3 demographic_data_gen.py 100
# Command-line argument(s): rec_count (number of records to generate as an integer)

# Write an application that creates a file containing demographic data.
# The application should accept a command line argument that specifies the number of records to generate.
# The application should write the demographic data to a file called 'demographic_data.csv'.
# The application should contain the following functions:

garystafford

# Purpose: Generate US residential address data
# Author: Gary A. Stafford and GitHub Copilot
# Date: 2023-04-13
# Usage: python3 residential_address_data_gen.py 100
# Command-line argument(s): rec_count (number of records to generate as an integer)

# Write an application that create a random list of united states addresses.
# The application should accept a command line argument that specifies the number of records to generate.
# Include address, city, state, zip code, country, and property type.
# Write the data to a csv file named 'address_data.csv'.

garystafford

# Purpose: Generate coffee shop sales data
# Author: Gary A. Stafford and GitHub Copilot
# Date: 2023-04-12
# Usage: python3 coffee_shop_data_gen.py 100
# Command-line argument(s): rec_count (number of records to generate as an integer)

# Write a program that creates synthetic sales data for a coffee shop.
# The program should accept a command line argument that specifies the number of records to generate.
# The program should write the sales data to a file called 'coffee_shop_sales_data.csv'.
# The program should contain the following functions:

garystafford