Total runs:
62.8M
Run Growth:
-2.2M
Growth Rate:
-3.54%
Sponsored by
APIMaster
BAAI / Emu3.5
Model's Last Updated: December 25 2025
any-to-any
Introduction of Emu3.5
Model Details of Emu3.5
Emu3.5: Native Multimodal Models are World Learners
Emu3.5 Team, BAAI
| 🔹 | Core Concept | Description |
|---|---|---|
| 🧠 | Unified World Modeling | Predicts the next state jointly across vision and language , enabling coherent world modeling and generation . |
| 🧩 | End-to-End Pretraining | Trained with a unified next-token prediction objective over interleaved vision–language sequences . |
| 📚 | Over 10T+ Multimodal Tokens | Pre-trained on over 10 trillion interleaved tokens from video frames and transcripts , capturing spatiotemporal structure . |
| 🔄 | Native Multimodal I/O | Processes and generates interleaved visual–text sequences without modality adapters or task-specific heads . |
| 🎯 | RL Post-Training | Large-scale reinforcement learning enhances reasoning , compositionality , and generation quality . |
| ⚡ | Discrete Diffusion Adaptation (DiDA) | Converts sequential decoding → bidirectional parallel prediction , achieving ≈20× faster inference without performance loss . |
| 🖼️ | Versatile Generation | Excels in long-horizon vision–language generation , any-to-image (X2I) synthesis, and text-rich image creation . |
| 🌐 | Generalizable World Modeling | Enables spatiotemporally consistent world exploration , and open-world embodied manipulation across diverse scenarios. |
| 🏆 | Performance Benchmark | Matches Gemini 2.5 Flash Image (Nano Banana) on image generation/editing , and outperforms on interleaved generation tasks . |
Table of Contents
1. Model & Weights
2. Quick Start
Environment Setup
git clone https://github.com/baaivision/Emu3.5
cd Emu3.5
pip install -r requirements.txt
pip install flash_attn==2.8.3 --no-build-isolation
Configuration
Edit
configs/config.py
to set:
-
Paths:
model_path,vq_path -
Task template:
task_type in {t2i, x2i, howto, story, explore, vla},use_imagecontrols<|IMAGE|>usage (set to true when reference images are provided) -
Sampling:
sampling_params(classifier_free_guidance, temperature, top_k/top_p, etc.)
Run Inference
python inference.py --cfg configs/config.py
Protobuf outputs are written to
outputs/<exp_name>/proto/
. For better throughput, we recommend ≥2 GPUs.
Visualize Protobuf Outputs
To visualize generated protobuf files:
python src/utils/vis_proto.py --input <input_proto_file> --output <output_dir>
3. Schedule
- Inference Code
- Advanced Image Decoder
- Discrete Diffusion Adaptation(DiDA)
4. Citation
@misc{cui2025emu35nativemultimodalmodels,
title={Emu3.5: Native Multimodal Models are World Learners},
author={Yufeng Cui and Honghao Chen and Haoge Deng and Xu Huang and Xinghang Li and Jirong Liu and Yang Liu and Zhuoyan Luo and Jinsheng Wang and Wenxuan Wang and Yueze Wang and Chengyuan Wang and Fan Zhang and Yingli Zhao and Ting Pan and Xianduo Li and Zecheng Hao and Wenxuan Ma and Zhuo Chen and Yulong Ao and Tiejun Huang and Zhongyuan Wang and Xinlong Wang},
year={2025},
eprint={2510.26583},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2510.26583},
}
Runs of BAAI Emu3.5 on huggingface.co
395
Total runs
-3
24-hour runs
2
3-day runs
23
7-day runs
15
30-day runs
More Information About Emu3.5 huggingface.co Model
Url of Emu3.5
Emu3.5 huggingface.co Url
Provider of Emu3.5 huggingface.co
Other API from BAAI
Updated:February 22 2024
Total runs:
17.1M
Run Growth:
-478.9K
Growth Rate:
-2.80%
Total runs:
10.1M
Run Growth:
-1.1M
Growth Rate:
-11.04%
Total runs:
9.8M
Run Growth:
-3.3M
Growth Rate:
-34.01%
Total runs:
4.6M
Run Growth:
-57.1K
Growth Rate:
-1.24%
Total runs:
2.4M
Run Growth:
-106.5K
Growth Rate:
-4.41%
Total runs:
712.1K
Run Growth:
-363.1K
Growth Rate:
-50.99%
Total runs:
619.2K
Run Growth:
-361.7K
Growth Rate:
-58.42%
Total runs:
333.8K
Run Growth:
129.4K
Growth Rate:
38.77%
Total runs:
193.4K
Run Growth:
-430.2K
Growth Rate:
-222.51%
Total runs:
161.8K
Run Growth:
-1.4K
Growth Rate:
-0.87%
Total runs:
82.0K
Run Growth:
-228.7K
Growth Rate:
-277.26%
Total runs:
57.9K
Run Growth:
-10.8K
Growth Rate:
-18.57%
Total runs:
16.6K
Run Growth:
28
Growth Rate:
0.17%
Total runs:
10.4K
Run Growth:
10.4K
Growth Rate:
100.00%
Total runs:
8.7K
Run Growth:
153
Growth Rate:
1.76%
Total runs:
8.7K
Run Growth:
190
Growth Rate:
2.18%
Total runs:
2.4K
Run Growth:
-4.0K
Growth Rate:
-161.66%
Total runs:
2.3K
Run Growth:
1.0K
Growth Rate:
42.74%
Total runs:
2.3K
Run Growth:
233
Growth Rate:
10.26%
Total runs:
1.2K
Run Growth:
271
Growth Rate:
23.32%
Total runs:
831
Run Growth:
419
Growth Rate:
50.42%
Total runs:
726
Run Growth:
726
Growth Rate:
100.00%
Total runs:
664
Run Growth:
0
Growth Rate:
0.00%
Total runs:
644
Run Growth:
0
Growth Rate:
0.00%
Total runs:
620
Run Growth:
-433
Growth Rate:
-69.84%
Total runs:
316
Run Growth:
-439
Growth Rate:
-138.92%
Total runs:
235
Run Growth:
89
Growth Rate:
38.36%
Total runs:
211
Run Growth:
101
Growth Rate:
47.87%
Total runs:
200
Run Growth:
51
Growth Rate:
25.50%
Total runs:
184
Run Growth:
57
Growth Rate:
30.65%
Total runs:
183
Run Growth:
51
Growth Rate:
28.02%