AINewsnow

Show HN: A decent text-to-image model trained for ~$20K (Apache 2.0 Weights)

This story is from 2026-11-04. It is preserved in the archive; the latest stories are on the live feed.

My brother and I run a 2-person lab that trains our own generative video models from scratch. The ultimate goal is a set of creative tools that make it easier for anyone to make animation. Video models today are too slow/expensive and lack sufficient controls. Creativity is an iterative process. Yo…

Read the full story at Hacker News Front Page ↗

Timeline · 1 report

  1. 2026-11-04 16:45 · Hacker News Front Page
    Show HN: A decent text-to-image model trained for ~$20K (Apache 2.0 Weights)

More stories

  1. Man sues OpenAI, alleging ChatGPT helped his wife plot to poison him — Bloomberg AI
  2. AI stocks slide globally after Democrats' midterm wins spark tech rout — AP News
  3. MCP servers and tooling expand for Claude Code, Cursor and rival coding agents — DEV Community — AI
  4. VIDRAFT's Darwin-180B-RSI-R3 Ranks Among Top Open-Weight Models in Math and Science Reasoning — DEV Community — Machine Learning
  5. Thinking Machines releases Inkling 2 Small, a 594B-parameter open-weight model, amid $5B funding round — Techmeme
  6. 48-Hour Field Notes Series Documents Pitfalls of Running AI Jobs on Free Tiers — DEV Community — AI
  7. Anthropic IPO valuation expectations fall to $1–1.3 trillion after AI stock selloff — Financial Times AI
  8. Hydra-PSIE expands 'Coeziune OM–IA' DOI registry to 37 published works — DEV Community — AI

Get the daily brief of stories like this at 6:30 every morning →