StereoscopeGenerator - ComfyUI Node for Stereoscopic Image Generation
======================================================================

This project includes code from the following sources:

1. prompt-to-prompt (https://github.com/google/prompt-to-prompt)
   Copyright 2022 Google LLC
   Licensed under the Apache License, Version 2.0

   Files derived from prompt-to-prompt:
   - diffusion_utils.py: Contains diffusion_step(), init_latent(), and
     register_attention_control() functions adapted from ptp_utils.py
   - inversion.py: Contains NullInversion class implementing DDIM inversion
     with null-text optimization adapted from null_text_w_ptp.ipynb

   Modifications made:
   - Extracted only the functions needed for this project
   - Added type hints and docstrings
   - Removed unused imports and visualization functions
   - Fixed deprecation warning for unet.in_channels access
   - Added ComfyUI model compatibility via wrapper classes
   - Implemented gradient-enabled mode using functional_call for ComfyUI models
   - Added optional null-text optimization toggle

2. StereoDiffusion (https://github.com/lez-s/StereoDiffusion)
   License: MIT License

   Files derived from StereoDiffusion:
   - stereo_utils.py: Contains stereo_shift_torch(), BNAttention class,
     register_attention_editor_diffusers(), and restore_attention() functions

   Modifications made:
   - Fixed bug in restore_attention() using sim instead of attn
   - Fixed numpy/torch dtype compatibility issue in _norm_depth()
   - Renamed parameter from 'sacle_factor' to 'scale_factor' (typo fix)
   - Added type hints and docstrings
   - Removed dependency on stablediffusion submodule (DDIMSampler)

For the full Apache 2.0 license text, see licenses/APACHE-2.0.txt
