Modelsslug: dreamina-seedance-2-5

Dreamina Seedance 2.5

Video generation model from ByteDance Seed supporting text prompts with reference image conditioning.

Curated Intelligence

1 items · Page 1/1
Artificial Analysis (@ArtificialAnlys)T1·Models
72 pts
LLMs Generate 3D Scenes as Code to Challenge Video Models

Artificial Analysis ran a head-to-head test asking OpenAI's GPT-6.2 Astra to build three 3D scenes (Sydney Opera House, an exploded mechanical watch, and a dragon attacking a medieval town) as three.js code, then flew a scripted camera through each in a browser at 15s, 1080p, 24fps. ByteDance's Dreamina Seedance 2.5 received the same camera path as a text prompt with route reference images at identical settings, probing whether LLMs can compete with dedicated video generation models.