Same photo test: fable 5.2 nails image-to-illustration where opus 5.5 fell short
yuwen_lu_ · x · 2026-11-11
User yuwenlu retried the same photo-to-illustration task: opus 5.5 produced a mediocre result three weeks ago, while fable 5.2 nailed it today on the identical input. Side-by-side images show fable 5.2 far closer to the original in composition, mountains, and the dog's pose.
More from Models
- Grok Bot team teases multiple improvements on the way — mattyp · 2026-11-11
- Alibaba ships Qwen Code 1.0, now runs three competing coding tools; Qwen4 Max Preview panned — teortaxesTex · 2026-11-11
- Meituan's LongCat-2.5 tops 3DCodeBench at 55.4, open-sourced under MIT — dr_cintas · 2026-11-11
- OpenAI researcher will bet $100k that weight-space editing hype is overblown — willdepue · 2026-11-11
- Gemini 4 Carbon scores 57.3 vs top model's 58 at 1/4.5 the cost in real-repo bug test — koraykv · 2026-11-11
- User ditches Grok 4.7 for Claude after testing: switching from Cursor's $200/mo plan — pramodk73 · 2026-11-11