DobidopandClaude
c2b3bb5a50
Combines three powerful stereoscopic tools into one comprehensive package: 1. Core Stereo Generation - Depth-based stereo conversion with GPU acceleration - Advanced fill techniques (Polylines, GPU Warp, Hybrid Edge, etc.) - Edge-aware depth blurring for artifact reduction - Side-by-Side, Top-Bottom, and Red-Cyan Anaglyph output formats 2. Native VR Viewing (Optional - requires PyOpenXR) - Auto-launch directly into VR headset without browser - Support for all VR headsets (Quest, Vive, Index, WMR) - Multiple projection types (Flat, Curved, 180° Dome, 360° Sphere) - Image and video playback support 3. StereoDiffusion AI (Optional - requires diffusers) - AI-powered stereo generation using diffusion models - DDIM inversion with null-text optimization - Bilateral Neighbor Attention for stereo consistency - Works with ComfyUI MODEL/CLIP/VAE or HuggingFace models Changes: - Added native_viewer/ module with PyOpenXR implementation - Added native_nodes.py with 3 VR viewer nodes - Added stereodiffusion_nodes.py with AI stereo generation - Added supporting modules: model_wrappers, model_loader, inversion, stereo_utils, diffusion_utils - Updated __init__.py with graceful optional dependency handling - Consolidated all requirements into single requirements.txt - Comprehensive README with setup guides and troubleshooting - Added NOTICE and licenses/ for proper attribution The package now offers 6+ nodes total with modular installation options. Users can install just the base, or add VR viewing and/or AI generation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
40 lines
1.7 KiB
Plaintext
40 lines
1.7 KiB
Plaintext
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
|