Grok Imagine 2.0 Released: Debuts at #2 on Text-to-Image and Edit Arenas
jefffhj · x · 2026-08-08
xAI's Grok has released Imagine Image 2.0, its next-generation image model featuring precision editing, crisp text rendering, and improved factuality.
On the Arena leaderboard, the model debuted at #2 in Text-to-Image with 1320 points, performing strongly across categories like art, portraits, anime, and photorealism. It also secured the #2 spot (1439 pts) in the Image Edit Arena. Currently, the model is only available via their app without API access.
More from Multimodal
- ForcingBooster halves computation of autoregressive video diffusion with patch-wise denoising — VAST-AI · 2026-10-16
- Tokyo's Gemini AI Photo Booth turns visitors into plush toys and dioramas — bradneuberg · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16
- Indie Creator Builds an AI-Native Animated Show Solo — ComprehensiveLime654 · 2026-10-16
- Ideogram teases 4.5 arrival and open weights: 'Not yet, but soon' — East_Shoe8814 · 2026-10-16
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16