Chaorui Deng*, Deyao Zhu*, Kunchang Li*, Chenhui Gou*, Feng Li*, Zeyu Wang, Shu Zhong, Weihao Yu, Xiaonan Nie, Ziang Song, Guang Shi 📧 , Haoqi Fan 🎩
contact: shiguang.sg@bytedance.com
We present BAGEL, an open‑source multimodal foundation model with 7B active parameters (14B total) trained on large‑scale interleaved multimodal data. BAGEL outperforms the current top‑tier open‑source VLMs like Qwen2.5-VL and InternVL-2.5 on standard multimodal understanding leaderboards, and delivers text‑to‑image quality that is competitive with strong specialist generators such as SD3. Moreover, BAGEL demonstrates superior qualitative results in classical image‑editing scenarios than the leading open-source models. More importantly, it extends to free-form visual manipulation, multiview synthesis, and world navigation, capabilities that constitute "world-modeling" tasks beyond the scope of previous image-editing models. The figure below showcases BAGEL's qualitative performance.
BAGEL adopts a Mixture-of-Transformer-Experts (MoT) architecture to maximize the model’s capacity to learn from richly diverse multimodal information. Following the same principle of capacity maximization, it utilizes two separate encoders to capture pixel-level and semantic-level features of an image. The overall framework follows a Next Group of Token Prediction paradigm, where the model is trained to predict the next group of language or visual tokens as a compression target.
BAGEL scales MoT’s capacity through Pre-training, Continued Training, and Supervised Finetuning on trillions of interleaved multimodal tokens spanning language, image, video, and web data. It surpasses open models on standard understanding and generation benchmarks and demonstrates advanced in-context multimodal abilities like free-form image editing, future frame prediction, 3D manipulation, world navigation, and sequential reasoning.
As we scale up BAGEL’s pretraining with more multimodal tokens, we observe consistent performance gains across understanding, generation, and editing tasks. Different capabilities emerge at distinct training stages—multimodal understanding and generation appear early, followed by basic editing, while complex, intelligent editing emerges later. This staged progression suggests an emergent pattern, where advanced multimodal reasoning builds on well-formed foundational skills. Ablation studies further show that combining VAE and ViT features significantly improves intelligent editing, underscoring the importance of visual-semantic context in enabling complex multimodal reasoning and further supporting its role in the emergence of advanced capabilities.
Call for Bad Cases: If you have encountered any cases where the model performs poorly, we would greatly appreciate it if you could share them in the issue#11 or Discord.
About Inference Hyperparameters:
cfg_text_scale: Controls how strongly the model follows the text prompt.1.0disables text guidance. Typical range:4.0–8.0.cfg_image_scale: Controls how much the model preserves input image details.1.0disables image guidance. Typical range:1.0–2.0.cfg_interval: Fraction of denoising steps where CFG is applied. Later steps can skip CFG to reduce computation. Typical:[0.4, 1.0].timestep_shift: Shifts the distribution of denoising steps. Higher values allocate more steps at the start (affects layout); lower values allocate more at the end (improves details).num_timesteps: Total denoising steps. Typical:50.cfg_renorm_min: Minimum value for CFG-Renorm.1.0disables renorm. Typical:0.cfg_renorm_type: CFG-Renorm method:global: Normalize over all tokens and channels (default for T2I).channel: Normalize across channels for each token.text_channel: Likechannel, but only applies to text condition (good for editing, may cause blur).
- If edited images appear blurry, try
globalCFG-Renorm, decreasecfg_renorm_minor decreasecfg_scale.
1️⃣ Set up environment
git clone https://github.com/bytedance-seed/BAGEL.git
cd BAGEL
conda create -n bagel python=3.10 -y
conda activate bagel
pip install -r requirements.txt2️⃣ Download pretrained checkpoint
from huggingface_hub import snapshot_download
save_dir = "/path/to/save/BAGEL-7B-MoT"
repo_id = "ByteDance-Seed/BAGEL-7B-MoT"
cache_dir = save_dir + "/cache"
snapshot_download(cache_dir=cache_dir,
local_dir=save_dir,
repo_id=repo_id,
local_dir_use_symlinks=False,
resume_download=True,
allow_patterns=["*.json", "*.safetensors", "*.bin", "*.py", "*.md", "*.txt"],
)3️⃣ Go to inference.ipynb to start playing with BAGEL!
4️⃣ Use Gradio WebUI to start playing with BAGEL!
pip install gradio
python app.pybash scripts/train.shYou can replace the variables in the script with your own before running. See TRAIN for more details.
We provide the scripts for evaluating VLM, T2I and Editing benchmarks. Please See EVAL for more details.
| Model | MME ↑ | MMBench ↑ | MMMU ↑ | MM-Vet ↑ | MathVista ↑ |
|---|---|---|---|---|---|
| Janus-Pro-7B | - | 79.2 | 41.0 | 50.0 | – |
| Qwen2.5-VL-7B | 2347 | 83.5 | 58.6 | 67.1 | 68.2 |
| BAGEL | 2388 | 85.0 | 55.3 | 67.2 | 73.1 |
| Model | GenEval ↑ | WISE ↑ |
|---|---|---|
| Janus-Pro-7B | 0.80 | 0.35 |
| SD3-Medium | 0.74 | - |
| FLUX-1-dev | 0.82 | 0.50 |
| BAGEL | - | 0.52 |
| BAGEL + CoT | 0.88 | 0.70 |
| Model | GEdit-Bench-EN (SC) ↑ | GEdit-Bench-EN (PQ) ↑ | GEdit-Bench-EN (O) ↑ | IntelligentBench ↑ |
|---|---|---|---|---|
| Step1X-Edit | 7.09 | 6.76 | 6.70 | 14.9 |
| Gemini-2-exp. | 6.73 | 6.61 | 6.32 | 57.6 |
| BAGEL | 7.36 | 6.83 | 6.52 | 44.0 |
| BAGEL+CoT | – | – | – | 55.3 |
@article{deng2025bagel,
title = {Emerging Properties in Unified Multimodal Pretraining},
author = {Deng, Chaorui and Zhu, Deyao and Li, Kunchang and Gou, Chenhui and Li, Feng and Wang, Zeyu and Zhong, Shu and Yu, Weihao and Nie, Xiaonan and Song, Ziang and Shi, Guang and Fan, Haoqi},
journal = {arXiv preprint arXiv:2505.14683},
year = {2025}
}BAGEL is licensed under the Apache 2.0.