A mysterious new image generation model has appeared
A mysterious new image generation model has appeared | TechCrunch
A mysterious new image generation model is beating models from Midjourney, Black Forest Labs, and OpenAI on the crowdsourced Artificial Analysis benchmark.
The model, which goes by the name “ red_panda,” is around 40 Elo points ahead of the next-best-ranking model, Black Forest Labs’ Flux1.1 Pro, on Artificial Analysis’ text-to-image leaderboard. Artificial Analysis uses Elo, a ranking system originally developed to calculate the relative skill level of chess players, to compare the performance of the various models it tests.
Deedy Das (opens in a new window)
Similar to the community AI benchmark Chatbot Arena, Artificial Analysis ranks models through crowdsourcing. For image models, Artificial Analysis selects two models at random and feeds them a unique prompt. Then, it presents the prompt and resulting images, and users choose which they think better reflects the prompt.
Granted, there’s some bias in this voting process. Artificial Analysis’ voters are AI enthusiasts, for the most part, and their choices might not reflect the preferences of the wider community of generative AI users.
But red_panda is also one of the better-performing models on the leaderboard in terms of its generation speed. The model takes a median of around 7 seconds to generate an image — over 100 times faster than OpenAI’s DALL-E 3.
Neuralithic (opens in a new window)
So, where did red_panda come from? Which company made it? And when can we expect it be released? All good questions. AI labs increasingly use community benchmarks to drum up anticipation ahead of an announcement, though, so it might not be long before we find out.
Related Knowledge Center: ENERGY BASICS: nuclear
Nuclear energy provides almost 20 percent of the U.S. electricity supply. Advocates have called for an expanded role for nuclear as an emissions-free fuel source. But the economics of building new reactors are daunting. In addition, lingering safety concerns are an institutionalized part of the calculation of nuclear regulation, and highly radioactive nuclear waste remains a can that public officials have been inclined to kick down the road. The Energy Information Administration projects a sharp decline in nuclear power generation over the next decade, as new nuclear plants — two are planned — are more than offset by anticipated retirements of several operating reactors.