All systems operationalAI Agent Automation Platform

Xianshe Model Hub

Find the right model.
Download more easily.

Review model capabilities, use cases and requirements, then download a pinned version from a China-based mirror.

Chinese documentationOriginal sourceDirect mirror downloads
Search by taskNo model name needed

What do you need a model for?

Search by model name, author or use case

5Current results
Pinned revisionKeep matching files together
Direct from mirrorNo Xianshe relay
Browse by Use CaseChoose a task, then explore models
Clear filters

Standard means not labeled as uncensored; it is not official certification. Uncensored / Modified follows source labels such as uncensored or abliterated and does not verify quality or safety. Quantized and fine-tuned categories may overlap.

All Models

Browse the Model Catalog

Embodied AI

MiniCPM-RobotManip

OpenBMB
ModelScope source
Standard

MiniCPM-RobotManip MiniCPM-RobotManip是一个15亿参数的视觉-语言-动作模型,用于具身操作任务。 通用操作能力:一个统一的15亿参数通用策略,使用同一套权重处理所有下游任务,在代表性评估中优于更大的模型如π₀.₅和Qwen-VLA。

Chinese documentationPinned revisionDownload instructions

Embodied AI

flux-3-action-base

black-forest-labs
国内镜像可用
Standard

FLUX 3 Action Base FLUX 3 Action 是一个开源权重的7B世界动作模型。该模型用于机器人控制,属于适配组件而非完整的机器人策略。 模型接收摄像头画面、机器人状态和文本指令,输出下一段动作以及与动作同步的去噪视频帧。基础模型包含457个张量,分为视频流、文本流、共享动作主干和ee50/gaming动作头。新肢体形态需要配备专用的动作头。

Chinese documentationPinned revisionDownload instructions

Embodied AI

flux-3-action-so101

black-forest-labs
国内镜像可用
Community Derivative

FLUX 3 Action 是一个开源权重的 7B 世界动作模型。该模型接收摄像头画面、机器人状态和文本指令,返回下一段动作预测,同时生成去噪后的下一帧视频。 根据视觉观察、机器人状态和文本指令预测动作序列 采用 SO-101 策略,包含检查点自带的观察历史、摄像头布局和归一化参数

Chinese documentationPinned revisionDownload instructions

Embodied AI

flux-3-action-droid

black-forest-labs
国内镜像可用
Community Derivative

FLUX 3 Action DROID FLUX 3 Action 是一个开源的 7B 参数世界动作模型。该模型接收摄像头画面、机器人状态和文本指令,输出下一段动作,并与下一帧视频画面一起去噪。该模型基于 DROID 数据集微调,在 RoboLab-120 基准测试中以 42.92% 的任务成功率排名第一。 该模型为世界动作模型(WAM),能够同时预测未来画面和动作。与传统的视觉语言动作模型(VLA)不同,WAM 将动作预测与视频生成结合在一起。

Chinese documentationPinned revisionDownload instructions

Embodied AI

MuseVLA

microsoft
国内镜像可用
Standard

MuseVLA:用于机器人操作的自适应多模态传感视觉-语言-动作模型 MuseVLA是一种用于机器人操作的自适应多模态传感视觉-语言-动作模型。基于VITRA构建,MuseVLA将新型传感器视为按需工具,首先选择任务所需的模态,将选定的传感器观测结果与RGB图像对齐,然后生成机器人动作。 支持RGB、热传感、声学传感和mmWave雷达传感等多种传感器模态。在热传感、声学传感和雷达传感引导的机器人操作任务中,平均成功率达到80.6%。在未见过的传感器引导任务中,平均成功率为66

Chinese documentationPinned revisionDownload instructions
Can't Find the Model You Need?

Submit the repository ID and use case for review.

Suggest a Model

Sign in to suggest a model for the catalog.

Models and files belong to their original authors. Link checks do not certify safety or runtime compatibility. Read the author's documentation and license before use.

Back to top