95708ad220
sd_local: the repose stack as an operator — Hyper_Realism + repose/models/lora + optional OpenPose T-pose template + IP-Adapter ref. Absolute venv path = primary-only by design. Verified: 512x640 portrait in one shot. stereo_depth: side-by-side stereo video/frame → per-frame SGBM disparity maps + colored midframe .ply for Blender displace/point-cloud work. venvs/stereo (opencv-headless). Verified on a synthetic 24px-disparity plate: subject bright, zero-disparity bg black, 1.4MB cloud. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
21 lines
1.2 KiB
JSON
21 lines
1.2 KiB
JSON
{
|
|
"id": "stereo_depth",
|
|
"name": "Stereo SBS → depth + point cloud (local)",
|
|
"category": "video-prep",
|
|
"description": "Side-by-side stereoscopic video (or one SBS frame) → per-frame disparity/depth maps via OpenCV StereoSGBM + a colored .ply point cloud of the middle frame for Blender. TRUE geometric depth from the L/R eye shift — no AI hallucination. Uncalibrated SBS rips aren't rectified, so expect relief-map depth (great for Displace-modifier planes), not survey-grade geometry. Output: depth preview mp4 + mid-frame .ply + zipped depth PNGs.",
|
|
"accepts": ["video", "image"],
|
|
"produces": ["archive"],
|
|
"resources": "cpu",
|
|
"entry": "run.py",
|
|
"python": "venvs/stereo/bin/python",
|
|
"params_schema": {
|
|
"type": "object",
|
|
"properties": {
|
|
"max_frames": {"type": "integer", "default": 120, "description": "Cap processed frames"},
|
|
"num_disp": {"type": "integer", "default": 128, "description": "Disparity search range (multiple of 16; raise for close subjects)"},
|
|
"block": {"type": "integer", "default": 5, "description": "SGBM block size (odd, 3-11)"},
|
|
"layout": {"type": "string", "enum": ["sbs", "tab"], "default": "sbs", "description": "side-by-side or top-and-bottom stereo"}
|
|
}
|
|
}
|
|
}
|