I built a local Elixir/Python pipeline to curate 14,000 RAW photos
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
I had 14,000 photos sitting on a drive and wanted an excuse to play with local vision models and Elixir/Phoenix. I originally tried to get LLaVA to tell me if a photo was 'good' or matched my style, but quickly learned that LLMs have terrible taste. I ended up demoting the LLM to just extract metadata, and built a custom CLIP/Ridge Regression pipeline to actually learn my preferences based on how I rate things.The stack is Phoenix/Oban on the orchestrator side, and Python/FastAPI/Instructor for the AI workers. Happy to answer any questions about the architecture, fighting with local RAW file ingestion, or the pains of Pydantic validation with open weights.
HN · launched Apr 20, 2026 · 5 upvotes (top 89%) · 1 view
Niche: image processing and editing tools · 260 launches, 21 in the last 7 days ▼ -28% · Explore this niche →
Category and tags
- Media & entertainment
- Workflow automation
- Prosumer
- Not AI
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 260 launches in image processing and editing tools →
Could you build this?
Yes The project is a personal local script pipeline combining an Elixir/Phoenix gallery with a Python worker script running local CLIP and LLaVA models via Ollama or PyTorch.
Discussion
2 comments analyzed.
Concerns raised: Network latency impact, RAM constraints for metadata extraction, RAW file processing overhead
Feature requests: Native RAW file conversion in Elixir
Competitors
Other products that read as similar to this one : 280 launches clear the similarity bar, closest 8 shown.
Attention rank: #235 of 281 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 171 days after the earliest competitor.
- I run 30B 22tok/s, 109tok/s not novel,6GB/16GB RAM overcoming llama.cpp · hn · 2026-07-29 · 5 upvotes · similarity 0.44
- L88 · hn · 2026-02-24 · 12 upvotes · similarity 0.44
- I created a RAW to HDRI stacker in (mostly) Common Lisp · hn · 2026-06-05 · 35 upvotes · similarity 0.43
- Local text, image, video, music and 3D from one CLI, no Python · hn · 2026-07-30 · 16 upvotes · similarity 0.42
- An unmetered LLM API–$6/month, no token tracking, no limits · hn · 2026-07-06 · 12 upvotes · similarity 0.42
- I stumbled on a free AI photo enhancer · hn · 2025-12-03 · 6 upvotes · similarity 0.41
- Pyra · hn · 2026-04-17 · 13 upvotes · similarity 0.41
- Bulk Image Generator · hn · 2026-03-07 · 5 upvotes · similarity 0.41
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.