- Glif Standard Tests
- Upscale lowpoly
Upscale lowpoly
Every model got the same prompt. Here's what 6 models made, best first. GPT Image 2.6 is outlined.
Results
Won
GPT Image 2.6
#2 of 4
Clarity Upscaler
#2 of 4
P-Image Upscale
Scores combine expert human reviewers, expert AI judges and votes from the wider community, and we rank models on quality, speed and cost. See the full image upscaling leaderboard
What we look for
Keeps the low-poly game look; does not hallucinate realistic detail.
Prompt
“upscale”
Input
Tests for
Image editing, style