Training Krea 2: What matters in generative model training — Sangwu Lee, Krea.ai
The most reliable way to render a person is to render the most boring average person and put them in the center of the frame.
Sangwu Lee offers that as the price the big image models pay for consistency: ask a production model for a burning skull and every output comes back clean, competent, and nearly identical. Krea 2, whose medium variant is now open source, trades the other way, optimizing for fast generation and stylistic range so that a studio that does not yet know what it wants can actually explore. Most of the talk is about data, which he says twice over is basically everything once the architecture is locked. The examples are specific. A painting photographed on a wall is perfectly good training data except that captioners consistently omit the frame and the white wall behind it, so the model learns to hang every painting it generates. They refuse to train on AI generated images at all, because the aesthetic is sticky and you inherit somebody else's model. Deduplication runs on hashes first across two to ten billion images, then on embeddings for near duplicates.
The text is the source's own description of its publication. The content belongs to AI Engineer.
More from AI Engineer
Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca
AI Engineer 23 Oct
Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg
AI Engineer 23 Oct
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago