# Janus Series | Unified Multimodal Understanding And Generation Models **URL:** \ **Category:** Tools & Scripts\ **Tags:** tools, ai, gaming\ **Created:** [February 1, 2025, 1:59pm UTC](https://onehack.st/t/janus-series-unified-multimodal-understanding-and-generation-models/300127 "2025-02-01T13:59:21Z")\ **Posts on this page:** 1\ **Page:** 1
**Author:** ![Aina](https://onehack.st/user_avatar/onehack.st/aina/32/167469_2.png) [@Aina](https://onehack.st/u/Aina)\ **Post date:** [February 1, 2025, 1:59pm UTC](https://onehack.st/t/janus-series-unified-multimodal-understanding-and-generation-models/300127/1 "2025-02-01T13:59:22Z")
[![DeepSeek LLM](https://github.com/deepseek-ai/Janus/raw/main/images/logo.svg)](https://github.com/deepseek-ai/Janus/blob/main/images/logo.svg) * * * # 🚀 Janus-Series: Unified Multimodal Understanding and Generation Models [![Homepage](https://github.com/deepseek-ai/Janus/raw/main/images/badge.svg) ](https://www.deepseek.com/)[![Hugging Face](https://camo.githubusercontent.com/5e3115539d4583e22d65cb89eb1759e767cb9e1d70772923292fcfc80a654be4/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f25463025394625413425393725323048756767696e67253230466163652d446565705365656b25323041492d6666633130373f636f6c6f723d666663313037266c6f676f436f6c6f723d7768697465)](https://huggingface.co/deepseek-ai) [![Code License](https://camo.githubusercontent.com/d8caf1d64169802e8094bcf0013f0b54d3a9547263b4e59eb43531d7d77993e4/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f436f64655f4c6963656e73652d4d49542d6635646535333f26636f6c6f723d663564653533) ](https://github.com/deepseek-ai/Janus/blob/main/LICENSE-CODE)[![Model License](https://camo.githubusercontent.com/edb8b566827851c52a732ee62c71e1c0231f588d5181c5925a518d98f35b4ff4/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4d6f64656c5f4c6963656e73652d4d6f64656c5f41677265656d656e742d6635646535333f26636f6c6f723d663564653533)](https://github.com/deepseek-ai/Janus/blob/main/LICENSE-MODEL) [**📥 Model Download**](https://github.com/deepseek-ai/Janus#2-model-download) | [**⚡ Quick Start**](https://github.com/deepseek-ai/Janus#3-quick-start) | [**📜 License**](https://github.com/deepseek-ai/Janus#4-license) | [**📖 Citation**](https://github.com/deepseek-ai/Janus#5-citation) 🤗 Online Demo ([**Janus-Pro-7B**](https://huggingface.co/spaces/deepseek-ai/Janus-Pro-7B), [**Janus**](https://huggingface.co/spaces/deepseek-ai/Janus-1.3B), [**JanusFlow**](https://huggingface.co/spaces/deepseek-ai/JanusFlow-1.3B)) ## News **2025.01.27** : Janus-Pro is released, an advanced version of Janus, improving both multimodal understanding and visual generation significantly. See [paper](https://github.com/deepseek-ai/Janus/blob/main/janus_pro_tech_report.pdf) **2024.11.13** : JanusFlow is released, a new unified model with rectified flow for image generation. See [paper](https://arxiv.org/abs/2411.07975), [demo](https://huggingface.co/spaces/deepseek-ai/JanusFlow-1.3B) and [usage](https://github.com/deepseek-ai/Janus?tab=readme-ov-file#janusflow). **2024.10.23** : Evaluation code for reproducing the multimodal understanding results from the paper has been added to VLMEvalKit. Please refer to [this link](https://github.com/open-compass/VLMEvalKit/pull/541). **2024.10.20** : (1) Fix a bug in [tokenizer\_config.json](https://huggingface.co/deepseek-ai/Janus-1.3B/blob/main/tokenizer_config.json). The previous version caused classifier-free guidance to not function properly, resulting in relatively poor visual generation quality. (2) Release Gradio demo ([online demo](https://huggingface.co/spaces/deepseek-ai/Janus-1.3B) and [local](https://github.com/deepseek-ai/Janus#gradio-demo)). ## 1. Introduction [**Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling**](https://github.com/deepseek-ai/Janus/blob/main/janus_pro_tech_report.pdf) **Janus-Pro** is an advanced version of the previous work Janus. Specifically, Janus-Pro incorporates (1) an optimized training strategy, (2) expanded training data, and (3) scaling to larger model size. With these improvements, Janus-Pro achieves significant advancements in both multimodal understanding and text-to-image instruction-following capabilities, while also enhancing the stability of text-to-image generation. [![image](https://github.com/deepseek-ai/Janus/raw/main/images/teaser_januspro.png)](https://github.com/deepseek-ai/Janus/blob/main/images/teaser_januspro.png) [**Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation**](https://arxiv.org/abs/2410.13848) **Janus** is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder’s roles in understanding and generation, but also enhances the framework’s flexibility. Janus surpasses previous unified model and matches or exceeds the performance of task-specific models. The simplicity, high flexibility, and effectiveness of Janus make it a strong candidate for next-generation unified multimodal models. [![image](https://github.com/deepseek-ai/Janus/raw/main/images/teaser.png)](https://github.com/deepseek-ai/Janus/blob/main/images/teaser.png) [**JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation**](https://arxiv.org/abs/2411.07975) **JanusFlow** introduces a minimalist architecture that integrates autoregressive language models with rectified flow, a state-of-the-art method in generative modeling. Our key finding demonstrates that rectified flow can be straightforwardly trained within the large language model framework, eliminating the need for complex architectural modifications. Extensive experiments show that JanusFlow achieves comparable or superior performance to specialized models in their respective domains, while significantly outperforming existing unified approaches across standard benchmarks. This work represents a step toward more efficient and versatile vision-language models. [![image](https://github.com/deepseek-ai/Janus/raw/main/images/teaser_janusflow.png)](https://github.com/deepseek-ai/Janus/blob/main/images/teaser_janusflow.png) ## 2. Model Download We release Janus to the public to support a broader and more diverse range of research within both academic and commercial communities. Please note that the use of this model is subject to the terms outlined in [License section](https://github.com/deepseek-ai/Janus#5-license). Commercial usage is permitted under these terms. ### Huggingface | Model | Sequence Length | Download | | --- | --- | --- | | Janus-1.3B | 4096 | [🤗 Hugging Face](https://huggingface.co/deepseek-ai/Janus-1.3B) | | JanusFlow-1.3B | 4096 | [🤗 Hugging Face](https://huggingface.co/deepseek-ai/JanusFlow-1.3B) | | Janus-Pro-1B | 4096 | [🤗 Hugging Face](https://huggingface.co/deepseek-ai/Janus-Pro-1B) | | Janus-Pro-7B | 4096 | [🤗 Hugging Face](https://huggingface.co/deepseek-ai/Janus-Pro-7B) | ## 3. Quick Start ### Janus-Pro `` ```auto ``` ### Janus `` ```auto ``` ```auto ``` ```auto ``` ### JanusFlow `` ```auto ``` ## 4. License This code repository is licensed under [the MIT License](https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-CODE). The use of Janus models is subject to [DeepSeek Model License](https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL). ## 5. Citation ```auto @article{chen2025janus, title={Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling}, author={Chen, Xiaokang and Wu, Zhiyu and Liu, Xingchao and Pan, Zizheng and Liu, Wen and Xie, Zhenda and Yu, Xingkai and Ruan, Chong}, journal={arXiv preprint arXiv:2501.17811}, year={2025} } @article{wu2024janus, title={Janus: Decoupling visual encoding for unified multimodal understanding and generation}, author={Wu, Chengyue and Chen, Xiaokang and Wu, Zhiyu and Ma, Yiyang and Liu, Xingchao and Pan, Zizheng and Liu, Wen and Xie, Zhenda and Yu, Xingkai and Ruan, Chong and others}, journal={arXiv preprint arXiv:2410.13848}, year={2024} } @misc{ma2024janusflow, title={JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation}, author={Yiyang Ma and Xingchao Liu and Xiaokang Chen and Wen Liu and Chengyue Wu and Zhiyu Wu and Zizheng Pan and Zhenda Xie and Haowei Zhang and Xingkai yu and Liang Zhao and Yisong Wang and Jiaying Liu and Chong Ruan}, journal={arXiv preprint arXiv:2411.07975}, year={2024} } ``` ## 6. Contact If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com). ## GitHub: > **[GitHub - deepseek-ai/Janus: Janus-Series: Unified Multimodal Understanding and...](https://github.com/deepseek-ai/Janus)** > > Janus-Series: Unified Multimodal Understanding and Generation Models