Apple ADM 3 Cloud's weakest editing skill is reframing: #60 of 80 in composition and framing
ArtificialAnlys · x · 2026-11-12
Continuing its teardown of Apple's ADM 3 Cloud, Artificial Analysis notes that generating images from scratch is the harder job: the model sits in the bottom quarter of AA-Image-T2I v2.1.
By use case, the Consumer category — everyday images people make for fun — ranks #86 of 107, while its best use case, Retail & Ecommerce, is #63.
Among editing actions, Composition & Framing is its weakest skill at #60 of 80: the model slips whenever an edit requires reframing the shot.
Related event: Apple ADM 3 Cloud tested: 42nd in image editing, 85th in text-to-image(7 posts)→
More from Multimodal
- Izwi: open-source offline voice cloning in Rust, runs on 16GB M1 Pro — zinyando · 2026-11-12
- MiniMax H3 Image generates 3D game scenes in 10s, over 3x faster than GPT Image — HeyToha · 2026-11-12
- Dev releases local world model turning any image into interactive video, runs on RTX 3060 — lucidml_lover · 2026-11-12
- Ex-Meta CV researcher builds AdaL v2, a chat-driven video agent harness for GTM — Scobleizer · 2026-11-12
- MiniMax H3 image gen runs locally on AMD RX 9070, 25-30s per 4MP image — omglionheaded · 2026-11-12
- One reference, one prompt, three image models: side-by-side Nano Banana Pro vs GPT Image 2.6 test — gizakdag · 2026-11-12