Products9月25日 06:01

Runway 实测 Model Router：250 个 image-to-video 提示词下的成本与可用性对比

Official accountRunway ML@runwayml

Post

View the post

Why we picked it

Runway 拿 250 个真实提示词做了对比测试，想省视频生成钱的可以看看 Model Router 和 SOTA 基线差多少。

Runway 用 250 个 image-to-video 提示词测试了 Model Router 的表现。测试将 Model Router 与一个 SOTA 视频模型基线对比，考察两点：成本降幅和生产可用性。

Body

结论方向是 Model Router 在保持产出可用于生产的画质前提下降低了成本。

Original · Runway ML

Across 250 image-to-video prompts, we evaluated how Model Router reduces cost and holds production usability in comparison to a SOTA model baseline. Read more at the link below.📊 5 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Runway, Model Router, video generation, image-to-video.

Source attribution: curated from Runway ML (@runwayml).

#Runway #Model Router #video generation #image-to-video

Keep reading

Recent stories with the same tag or section

Models BuildersMulti-source18:01

Chinese contentRunway 开源机器人模型 Praxis-1，登顶 RoboLab-120 基准

做视频生成的 Runway 出了个机器人模型，权重和代码全开源，Apache 2.0 随便用，还在 Nvidia 的 RoboLab-120 上拿了 World Action Model 类别第一。机器人方向的研究者和创业公司可以直接下载来微调试试。

#Runway #Praxis-1 #open-source models #robots

Event

Official accountDecoder@Tomislav BezmalinovićSource

Models BuildersMulti-sourceSelected23:49

Runway Releases Praxis-1, a 27B MoE Video-Action Diffusion Transformer

Joint video-and-action prediction suggests Runway is steering its research toward world models that could serve robotics and simulation, not just media generation. Developers and researchers working on embodied AI or interactive video should read the technical report for architectural details unavailable in most commercial releases. It offers a direct comparison point against open world-model efforts that typically disclose far less about training design.

#Runway #Praxis-1 #video generation #world models

Event

Official accountRunway ML@runwaymlSource

Models BuildersMulti-sourceSelected23:48

Runway's Praxis-1 robotics model now runs on SO-101 hardware

Running on one RTX 5090 means hobbyists and university labs can now deploy a foundation robotics model without data-centre budgets, a sharp contrast to closed offerings from physical-AI startups. Teams using Hugging Face's LeRobot stack can clone the checkpoint and follow the published setup instructions to get a SO-101 arm running the same day. Watch this space as community-dataset-trained models challenge proprietary robotics stacks.

#Praxis-1 #SO-101 #LeRobot #Runway

Event

Official accountRunway ML@runwaymlSource

Models Builders09:34

Chinese content字节跳动 Seedance 2.5 Flash 视频生成模型上线 Runway 平台

字节把 Seedance 2.5 Flash 接进了 Runway，做视频更快、更便宜。用 Runway 的创作者可以顺手试试它和自己常用模型的出片差异，多一个选项总没坏处。

#Seedance #Runway #video generation #ByteDance

Official accountRunway ML@runwaymlSource

Products Builders22:32

Chinese contentRunway 新增 3D 支持，集成 Tripo H3.1 生成 3D 模型

Runway 把 Tripo H3.1 接进来了，打字或传图就能出 3D 模型，还能选角度当参考接着生图生视频。做 3D 资产或视频分镜的人可以试试，导出也兼容其他 3D 软件，不用来回切工具。

#Runway #Tripo #3D generation #video generation

Official accountRunway ML@runwaymlSource

Models BuildersMulti-sourceSelected15:43

Runway releases Praxis-1 robot model with open weights

An open-weight, Apache 2.0 robot policy model that runs on a single RTX 5090 lowers the entry bar for robotics labs and hardware startups that cannot afford proprietary stacks. Teams building manipulation systems can fine-tune it locally instead of licensing closed models like GPT-6 Astra, which Runway claims is 51 times costlier per task. Builders tracking video-to-action transfer, an emerging alternative to pure imitation learning, should benchmark it on their own hardware.

#Praxis-1 #Runway #robot models #open-source models

Event

IT之家Source