My guess is that MidJourney has been doing a massive-scale reinforcement learning from human feedback ("RLHF") - possibly the largest ever for text-to-image.
When human users choose to upscale an image, it's because they prefer it over the alternatives. It'd be a huge waste not to use this as a reward signal - cheap to collect, and exactly aligned with what your user base wants.
The more users you have, the better RLHF you can do. And then the more users you gain.
— Jim Fan
Recent articles
- Image segmentation using Gemini 2.5 - 18th April 2025
- GPT-4.1: Three new million token input models from OpenAI, including their cheapest model yet - 14th April 2025
- CaMeL offers a promising new direction for mitigating prompt injection attacks - 11th April 2025