demo.git - Vide-coded 64k demo system

Age	Commit message (Expand)	Author
10 hours	docs(cnn_v3): add uv inline deps to train_cnn_v3.py + HOW_TO_CNN note	skal
10 hours	docs(cnn_v3): add Windows 10 + CUDA training section to HOW_TO_CNN §2	skal
10 hours	fix(cnn_v3): resize target to albedo dims when sizes differ	skal
11 hours	docs(cnn_v3): add full Old House example to HOW_TO_CNN §1b	skal
11 hours	fix(cnn_v3): native OPEN_EXR_MULTILAYER + quiet render + flexible channel names	skal
11 hours	docs(cnn_v3): blender4 alias + Blender 4.5 LTS requirement for training data	skal
13 hours	docs(cnn_v3): clarify --output is a base dir, not a frame_### pattern	skal
13 hours	docs(cnn_v3): update HOW_TO_CNN for Blender 5.x compatibility	skal
13 hours	fix(cnn_v3): blender_export --view-layer flag + fallback to layer[0]	skal
13 hours	feat(cnn_v3): gen_sample tool + 7 simple training samples	skal
34 hours	feat(cnn_v3): HTML WebGPU tool (index.html + shaders.js + tester.js)	skal
35 hours	feat(cnn_v3): export script + HOW_TO_CNN.md playbook	skal
35 hours	feat(cnn_v3): Phase 6 — training script (train_cnn_v3.py + cnn_v3_utils.py)	skal
35 hours	docs(cnn_v3): update CNN_V3.md + HOWTO.md to reflect Phases 1-5 complete	skal
36 hours	feat(cnn_v3): Phase 4 complete — CNNv3Effect C++ + FiLM uniform upload	skal
37 hours	feat(cnn_v3): Phase 3 complete — WGSL U-Net inference shaders	skal
2 days	feat(cnn_v3): Phase 1 complete - GBufferEffect integrated + HOWTO playbook	skal
3 days	docs(cnn_v3): full design doc — U-Net + FiLM architecture plan	skal