SiliconCloud上线加速版视频模型Mochi-1-Preview

近期，GenmoAI开源了视频生成模型mochi 1预览版（10B），具有高保真度的动作和强大的提示遵循能力，当前支持480p分辨率视频生成。今天，硅基流动SiliconCloud上线了推理加速版mochi-1-preview（价格为￥2.8/Video），免去开发者的部署门槛，只需在开发应用时轻松调用API，带来更高效的用户体验。平台还支持开发者自由对比体验数十款大模型，为你的生成式AI应用选择最佳实践。

在线体验
https://cloud.siliconflow.cn/playground/text-to-video/17885302647

API文档
https://docs.siliconflow.cn/capabilities/video

提示词：A tomato talking with a face　

提示词：A woman with light skin, wearing a blue jacket and a black hat with a veil, looks down and to her right, then back up as she speaks; she has brown hair styled in an updo, light brown eyebrows, and is wearing a white collared shirt under her jacket; the camera remains stationary on her face as she speaks; the background is out of focus, but shows trees and people in period clothing; the scene is captured in real-life footage.　

提示词：A clear, turquoise river flows through a rocky canyon, cascading over a small waterfall and forming a pool of water at the bottom.The river is the main focus of the scene, with its clear water reflecting the surrounding trees and rocks. The canyon walls are steep and rocky, with some vegetation growing on them. The trees are mostly pine trees, with their green needles contrasting with the brown and gray rocks. The overall tone of the scene is one of peace and tranquility.

感受一下在SiliconCloud上的mochi-1-preview在推理加速后的效果。

模型特点及性能

mochi 1基于非对称扩散Transformer（AsymmDiT）架构，简单且可修改。与领先的闭源模型相比，mochi 1具有较强的竞争力。提示遵循和动作质量是视频生成模型中两个最关键的能力。

提示遵循：与文本提示的对齐度极高，确保生成的视频准确反映给定的指令。这使用户能够详细控制角色、设定和动作。

动作质量：mochi 1以每秒30帧的平滑度最长生成长达5.4秒的视频，具有高度的时间连贯性和逼真的动作形态。Mochi模拟了流体动力学、毛发模拟等物理现象，并表现出一致、流畅的人类动作。

Token工厂SiliconCloud

Qwen2.5（7B）等20+模型免费用

作为一站式大模型云服务平台，SiliconCloud致力于为开发者提供极速响应、价格亲民、品类齐全、体验丝滑的模型API。除了mochi-1-preview，SiliconCloud已上架包括DeepSeek-V2.5-1210、Llama-3.3-70B-Instruct、HunyuanVideo、Marco-o1、fish-speech-1.5、QwQ-32B-Preview、Qwen2.5-Coder-32B-Instruct、Qwen2-VL、InternVL2、Qwen2.5-7B/14B/32B/72B、FLUX.1、InternLM2.5-20B-Chat、BCE、BGE、SenseVoice-Small、GLM-4-9B-Chat在内的数十种开源大语言模型、图片/视频生成模型、语音模型、代码/数学模型以及向量与重排序模型。 　

其中，Qwen2.5（7B）、Llama3.1（8B）等多个大模型API免费使用，让开发者与产品经理无需担心研发阶段和大规模推广所带来的算力成本，实现“Token 自由”。