--- license: other license_name: ltx-2-community license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x pipeline_tag: image-to-video tags: - video-generation - audio-video-generation - multi-reference - video-continuation - world-model - murea ---
Murea-InWorld — From imagination to living worlds # Murea-Fast **From imagination to living worlds with agents and fast video generation.** [![Website](https://img.shields.io/badge/Website-murea.ai-207D74?style=for-the-badge)](https://murea.ai/) [![Paper PDF](https://img.shields.io/badge/Paper-PDF-465D86?style=for-the-badge)](https://murea.ai/page/paper/InWorld-technical-report.pdf) [![GitHub code](https://img.shields.io/badge/Code-GitHub-182635?style=for-the-badge&logo=github&logoColor=white)](https://github.com/Murea-Labs/InWorld) [![Hugging Face weights](https://img.shields.io/badge/Weights-Murea--Fast-C18B2E?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/MureaLabs/InWorld) [![Code license](https://img.shields.io/badge/Code_License-Apache--2.0-526578?style=for-the-badge)](https://github.com/Murea-Labs/InWorld/blob/main/LICENSE) 🎬 [Demo](#demo) · 📦 [Checkpoint](#released-checkpoint) · 🚀 [Get started](#download-and-run) · 🌏 [中文简介](#中文简介) · ✉️ [Contact](mailto:labs@murea.ai)
Murea-InWorld turns actions and imagination into audiovisual stories. **Murea-Mind** plans each story beat, maintains explicit world memory, and checks generated observations. **Murea-Fast** brings those plans to life as video with synchronized sound, conditioned on text and ordered visual references. This repository hosts the released **Murea-Fast checkpoint**. The inference service, Murea-Mind application, tests, and deployment instructions are available in the [code repository](https://github.com/Murea-Labs/InWorld). Murea-Pro is evaluated in the technical report; its weights are not included in this release. ## 🎬 Demo [Watch the storytelling demo](https://github.com/user-attachments/assets/2617c0f3-ded2-4a8f-81bb-b77095c92b0e) · [Explore more worlds](https://murea.ai/#motion) ## ✨ Highlights - **Multi-reference audiovisual generation:** use ordered references for characters, objects, and locations, then describe actions and dialogue in the prompt. - **Video with synchronized sound:** generate audiovisual clips with an 8-step distilled sampler. - **Continuation:** extend a clip from a clean latent prefix derived from its last frames. - **Interactive worlds with Murea-Mind:** turn player actions into a continuing story with persistent entities, branching histories, and shared co-op adventures. ## 📦 Released checkpoint | Item | Details | | --- | --- | | Model | Murea-Fast | | File | [`murea-fast.safetensors`](https://huggingface.co/MureaLabs/InWorld/blob/main/murea-fast.safetensors) | | File size | 42,018,192,440 bytes, approximately 42.02 GB | | Sampling | 8 steps | | Validated output setting | 1280 × 704 pixels, 24 fps | | Example clip | 121 frames, approximately 5 seconds | | Continuation | 17-frame prefix; new video frames are generated after the prefix | | Runtime | The Murea-Fast service in the [GitHub repository](https://github.com/Murea-Labs/InWorld/tree/main/inference) | SHA-256: ```text 1a2c0d8e23032994b52f2c67e14c930d3be8224f321c51353f0a2954ccbb9385 ``` ## 🚀 Download and run ### 1. Download the weights ```bash python -m pip install -U huggingface_hub hf download MureaLabs/InWorld murea-fast.safetensors --local-dir ./weights ``` ### 2. Get the inference code ```bash git clone https://github.com/Murea-Labs/InWorld.git cd InWorld/inference ``` Follow the [deployment guide](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/deployment.md) to install the GPU environment and obtain the required tokenizer, text encoder, connectors, audio/video decoders, and vocoder. The checkpoint alone is not a complete inference installation. Set the absolute `python`, `model_dir`, `checkpoint`, and `runtime_dir` paths in `configs/single-gpu.json`. Set `checkpoint` to the downloaded `murea-fast.safetensors` file. Choose a configuration appropriate for the available GPUs and memory. After completing the environment and component setup: ```bash bash scripts/murea-fast verify /absolute/path/to/murea-fast.safetensors --sha256 bash scripts/murea-fast prepare --config configs/single-gpu.json bash scripts/murea-fast start --config configs/single-gpu.json curl --fail http://127.0.0.1:30260/health ``` For reference-conditioned generation and continuation, use the [inference quick start](https://github.com/Murea-Labs/InWorld/blob/main/inference/README.md#quick-start) and [HTTP API reference](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/api.md). To play stories in the browser, follow the [Murea-Mind quick start](https://github.com/Murea-Labs/InWorld/blob/main/agent/README.md#quick-start). ## 📊 Evaluation The technical report reports the following results for Murea-Fast: | Benchmark | Metric | Score | | --- | --- | ---: | | OpenS2V-Eval | Total | 64.98 | | OS2V-Pro | Aggregate | 69.9 | See the [technical report](https://murea.ai/page/paper/InWorld-technical-report.pdf) and [project results](https://murea.ai/#results) for the evaluation protocols and comparisons. ## 🖥️ Hardware and practical limits The released inference service has been validated on NVIDIA H20 GPUs in one-GPU and four-GPU configurations. Runtime and memory requirements depend on reference image sizes, clip length, parallelism, and software settings. Consult the [measured performance and memory results](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/performance.md) before choosing hardware. - The published checks cover 5-second clips on one H20 and clips up to approximately 20 seconds on four 141 GB H20 GPUs. These results do not establish compatibility with smaller-memory GPUs. - Continuation regenerates audio; continuous speech and sound across clip boundaries are not guaranteed. - Multiple subjects can merge or lose identity, and long stories can drift. The available deployment checks do not establish quality across all prompts or worlds. - The current service does not support frame interpolation or upscaling. Experimental acceleration settings need separate validation. ## 🌏 中文简介 **Murea-InWorld** 将文字行动与参考图像转化为持续发展的视听故事：**Murea-Mind** 负责世界记忆、剧情规划与生成结果检查，**Murea-Fast** 负责生成带同步声音的视频。 本模型仓库发布的是 **Murea-Fast** 权重 `murea-fast.safetensors`；Murea-Mind、推理服务和完整使用文档位于 [GitHub 代码仓库](https://github.com/Murea-Labs/InWorld)。论文中评测的 Murea-Pro 权重不包含在本次发布中。 - 支持有序多参考图条件、8 步蒸馏生成和视频续接。 - 已验证的输出设置为 1280 × 704、24 fps；显存与耗时请参阅实测记录。 - 下载权重后，还需按部署文档安装运行环境和配套组件。 - 续接时音频会重新生成，跨片段的语音和声音连续性不作保证。 [中文部署说明](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/deployment_zh.md) · [中文推理指南](https://github.com/Murea-Labs/InWorld/blob/main/inference/README_zh.md) · [Murea-Mind 中文说明](https://github.com/Murea-Labs/InWorld/blob/main/agent/README_zh.md) ## 📜 License The **InWorld code** is released under [Apache License 2.0](https://github.com/Murea-Labs/InWorld/blob/main/LICENSE). The **Murea-Fast weights and required base components** are governed by the [LTX-2.x Community License Agreement](https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x), as documented in the repository's [provenance and license notice](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/provenance.md#licenses). The code license does not replace the model-weight license. See the linked agreement for its use and redistribution terms. ## 📚 Citation ```bibtex @techreport{murealabs2026inworld, title = {InWorld: From Imagination to Living Worlds with Agents and Fast Video Generation}, author = {{Murea Labs}}, institution = {Murea Labs}, year = {2026}, url = {https://murea.ai/page/paper/InWorld-technical-report.pdf} } ``` ## ✉️ Contact Email: [labs@murea.ai](mailto:labs@murea.ai) Visit the [project website](https://murea.ai/) or open an [issue in the code repository](https://github.com/Murea-Labs/InWorld/issues) for questions and reproducible bug reports.