HYUNJUNGLEE
b9342f6726
S-CANVAS (Saman Corp.) — DXF + DEM + AI 기반 3D 조감도 생성 엔진. ~24k LOC Python (scanvas_maker.py 7072 LOC GUI + 구조물 파서/빌더 다수). 이 커밋은 7-iter cleanup이 적용된 상태로 import: - F821 8 + B023 6: 비동기 lambda + except/loop 변수 캡처 NameError (Py3.13에서 reproduce 확인된 진짜 버그) - RUF012 4 + RUF013 1: ClassVar / implicit Optional 명시화 - F811/B905/B904/F401/F841/W293/F541/UP/SIM/RUF/PLR 700+ cleanup/modernization 신규 파일: - ruff.toml: target=py313, Korean unicode/저자 스타일/도메인 복잡도 무력화 - requirements-py313.txt: pyproj>=3.7, scipy>=1.14, numpy>=2.0.2 (Py3.13 wheel) - .gitignore: gcp-key.json, 캐시, 백업, 생성 이미지 제외 검증: ruff 0 errors, py_compile 0 errors, import 33/33 OK on Py3.13.13. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
5 lines
1.2 KiB
Plaintext
5 lines
1.2 KiB
Plaintext
Transform this aerial/satellite terrain image into a high-quality photorealistic bird's-eye view rendering. IMPORTANT: Keep the EXACT same terrain layout, structures, roads, water bodies from the input image. Only enhance the visual quality - add realistic textures, lighting, vegetation detail, water reflections. Do NOT change the composition or add/remove any major features.
|
|
|
|
Style: oblique aerial perspective, 3/4 view showing terrain depth, bright daylight, clear blue sky, sharp shadows, vivid green vegetation, enhance the existing satellite terrain texture and details, maintain exact terrain shape, contours, and layout from the input image, preserve water bodies, roads, and structural positions precisely, do NOT add or remove any major landscape features, photorealistic architectural visualization, professional drone photography quality, 8K ultra sharp detail, high dynamic range, realistic vegetation depth and canopy textures, natural water reflections and surface detail
|
|
|
|
Negative: blurry, low quality, distorted, watermark, text, logo, cartoon, anime, illustration, painting, sketch, oversaturated, underexposed, noisy, artifacts, completely different scene, unrelated content, changed terrain layout, moved structures, wrong topology |