{"id":23676061,"url":"https://github.com/loglux/shutterstockimageanalyzer","last_synced_at":"2026-05-01T18:32:07.428Z","repository":{"id":270162824,"uuid":"908958941","full_name":"loglux/ShutterstockImageAnalyzer","owner":"loglux","description":"Shutterstock Image Analyzer is a Python tool that leverages AI to analyze images, generate Shutterstock-compatible metadata (description, keywords, categories), and save the output in CSV format for easy image contribution.","archived":false,"fork":false,"pushed_at":"2025-01-06T14:04:15.000Z","size":64,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-19T18:16:33.681Z","etag":null,"topics":["ai","artificial-intelligence","llama3-2-vision","ollama","ollama-api","ollama-client","photography","shutterstock"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/loglux.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-12-27T11:48:51.000Z","updated_at":"2025-01-06T14:04:18.000Z","dependencies_parsed_at":null,"dependency_job_id":"590cb5f7-f686-44b6-ad99-6e56841eca50","html_url":"https://github.com/loglux/ShutterstockImageAnalyzer","commit_stats":null,"previous_names":["loglux/shutterstockimageanalyzer"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loglux%2FShutterstockImageAnalyzer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loglux%2FShutterstockImageAnalyzer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loglux%2FShutterstockImageAnalyzer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loglux%2FShutterstockImageAnalyzer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/loglux","download_url":"https://codeload.github.com/loglux/ShutterstockImageAnalyzer/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239708987,"owners_count":19684168,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","artificial-intelligence","llama3-2-vision","ollama","ollama-api","ollama-client","photography","shutterstock"],"created_at":"2024-12-29T14:41:23.540Z","updated_at":"2026-05-01T18:32:07.416Z","avatar_url":"https://github.com/loglux.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Shutterstock Metadata Generator (Ollama)\n\nLocal Ollama vision models generate Shutterstock-ready metadata (description, keywords, categories, editorial flag, mature content, illustration) and append it to CSV.\n\n## Prerequisites\n- Python 3.10+ and Ollama running with a vision model (tested on `llama3.2-vision`).\n- Install deps (prefer a venv): `python -m pip install -r requirements.txt`\n\n## Quick Start\nDirectory run (recommended defaults):\n```bash\npython3 image_analyzer.py \\\n  --dir path/to/images \\\n  --csv shutterstock.csv \\\n  --base-url http://localhost:11434/ \\\n  --model llama3.2-vision \\\n  --num-predict 800 --top-k 150 --max-retries 3 \\\n  --resize-max 1024 --resize-quality 85\n```\nSingle image:\n```bash\npython3 image_analyzer.py --image path/to/img.jpg --csv out.csv --base-url http://localhost:11434/\n```\nOptions:\n- `--recursive` to include subfolders.\n- `--prompt-file` to override the default prompt.\n- `--hint` to add context for all images.\n- `--no-fallback` disables the safer second pass on failures; `--max-retries` sets initial attempts (fallback uses cooler options).\n- `--no-progress` for quiet output.\n\n## Prompt (summary)\n- Caption: one concise sentence \u003c200 chars, no filler/ellipsis/repeated adjectives; prefer exact names when clear.\n- Keywords: 7–50 unique, no placeholders/HTML/“...”, max 30 after dedup.\n- Categories: 1–2 from the fixed list only.\n- Booleans: `editorial`, `mature_content`, `illustration`.\n\n## Features\n- Keyword post-processing (dedup, drop junk, limit length) and category validation.\n- Optional resizing/caching (`.cache/resized`) to improve stability/speed on large images.\n- Fallback pass with safer generation options for initial failures.\n- Prompt compliance checker for generated CSVs.\n\n## Testing\n```bash\npython3 -m unittest tests/test_image_analyzer.py\n```\n\n## Notes\n- Generated artifacts (`shutterstock.csv`, `.cache/resized/`, sample image folders) are git-ignored by default.\n- Use `--no-fallback` or different options if you need to mirror upstream behavior exactly.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Floglux%2Fshutterstockimageanalyzer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Floglux%2Fshutterstockimageanalyzer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Floglux%2Fshutterstockimageanalyzer/lists"}