Blogger tests Opus 5.5 for video gen: better cinematic language, but expensive to sample
huangyun_122 · x · 2026-10-04
- Blogger huangyun122 shared videos generated directly by "Opus 5.5" with no multi-turn prompt tuning, arguing its grasp of cinematic language stands out, though sampling costs are high.
- He likens video models to camera brands: Seedance is currently the "Canon," and wonders if MiniMax could become the next "Sony."
More from Multimodal
- Grok Imagine quietly adds intermediate keyframes for video generation — mark_k · 2026-10-04
- Google quietly tests new Gemini 2.5 Flash image generation model on Arena — mornaji · 2026-10-04
- W.I.T.C.H. fan trailer made 95% locally: full AI video pipeline on a 4070 + 5060ti — No_Taste_4102 · 2026-10-04
- Balancing inpainting cadence in video: more frequent inpaints mean less smear but more hectic detail — matdryhurst · 2026-10-04
- User claims Suno has achieved 'musical AGI', composing better than 95% of people — astralmatrix · 2026-10-04
- "Bad Footage" Makes AI Video More Believable: A UFO Vlog Demo with Full Prompt — LudovicCreator · 2026-10-04