Same surreal prompt tested: MiniMax H3 passes while Kling and Seedance fail
charis_ai · x · 2026-09-10
Creator charisai tested a "simple yet surreal" video prompt shared by Umesh across multiple video models. MiniMax H3, with a slight prompt variation, produced the closest decent result, while both Kling and Seedance were "big ol' fails."
Another data point on how widely video models diverge on the same prompt — useful as a quick model-selection reference.
More from Multimodal
- Programmable World Model Separates Explicit State Evolution From Video Generation — Zheng-Hui Huang · 2026-09-10
- ByteDance's AgenticGen Uses Business Feedback and Human Rewards to Guide Ad Video Generation — ByteDance · 2026-09-10
- Flash-BoN: cheap drafts beat guided search for diffusion inference-time scaling, +8% AUC at scale — gowthami_s · 2026-09-10
- Alibaba open-sources 2 more speech enhancement models, completing a 7-model toolkit with 22ms echo cancellation — aigclink · 2026-09-10
- A 78-second AI food comedy: Pig Girl crashes a Viking winter feast — Substantial_Depth744 · 2026-09-10
- Shareable ChatGPT Prompt Turns Photos into Mecha-Style Art — Promptmethus · 2026-09-10