User verdict: Gemini best for video, ChatGPT's newest image model smartest for stills
dreamwieber · x · 2026-10-14
A user compares current AI generation tools: Gemini (Omni?) is the best video model right now, ChatGPT's newest image model is "incredibly smart" for stills, while MidJourney has good vibes but lacks the intelligence and coherence of frontier models.
More from Multimodal
- Kroma: a free ComfyUI workflow chaining Chroma and Krea 2 with 2x upscale — gabrielxdesign · 2026-10-14
- Open-source Fish Audio Drama 3 studio lets you design character voices in any language — camenduru · 2026-10-14
- AI parody gives James Bond a tiny new partner: a milk-sipping puppy — FrameTwistCreates · 2026-10-14
- WOVEN benchmark finds all 38 frontier MLLMs fail visual transition reasoning far below humans — MLL-Lab · 2026-10-14
- Low-poly previs plus Fal agent rendering with Seedream 5 and Seedance 2.5 — adamho · 2026-10-14
- Hands-on with PPT.AI: paste a link, get a 40-second concept video from your website — yihui_indie · 2026-10-14