Mask sensitive tokens, sanitize prompts, and add README documenting tech stack

[edumgt]

Motivation

• Remove hardcoded Hugging Face tokens from scripts to avoid leaking secrets and encourage environment-variable usage.
• Replace explicit/sexual prompt content with safe, non-explicit alternatives to sanitize repository content.
• Provide a short README describing the project, its tech stack, and quick-start guidance for contributors.

Description

• Replaced hardcoded HF_TOKEN assignments with HF_TOKEN = os.getenv("HF_TOKEN", "hf_***MASKED***") in 3.py, cpu.py, imgwork.py, and mp4make.py.
• Sanitized explicit prompts in 3.py by replacing sexually explicit text with neutral, non-explicit prompts.
• Added README.md describing repository purpose, core tech stack (diffusers, torch, opencv, Pillow, ffmpeg, ControlNet/OpenPose), file roles, runtime notes, and security/content-cleanup guidance.
• Kept original script structure and behavior while updating prompt text and secret handling.

Testing

• Ran syntax validation with python -m py_compile 3.py cpu.py imgwork.py mp4make.py, which completed without errors.
• Scanned for remaining hardcoded token patterns with rg (searching for hf_..., API keys, and token assignments) and found no matches after the changes.
• Verified the modified scripts load the HF_TOKEN variable via os.getenv (defaults to masked placeholder) so runtime behavior remains unchanged when a real token is provided.

---

Codex Task

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, you can upgrade your account or add credits to your account and enable them for code reviews in your settings.