This is my fork of Bagel, set up to run on multi-gpu inside runpod.io pod using the custom image:

madiator2011/better-pytorch\:cuda12.4-torch2.6.0

⚠️ Make sure to open port 7860.
RunPod users: set 7777,7680 in the pod's port field, if you want to use gradio ui.

I have specially compiled FlashAttention for this setup and provided an installation script in the Installation Notebook.

• Added multi-GPU support in both app.py and inference.ipynb.
• With help from Gemini 2.5, the model now supports multi-GPU inference.

with A40x2 machine the model was taking 64GB and inference was around 2 minutes per image.

Inside your pod, download the Raw Installation Notebook:

wget https://raw.githubusercontent.com/simsim314/Bagel/refs/heads/main/install.ipynb

Run all commands inside the notebook.

Then you can either:

• Run the Jupyter notebook: inference.ipynb

• Or launch the Gradio UI app.py:

  python app.py

The rest should be self-explanatory.

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.

We sincerely thank all contributors from the open community for their valuable support.

• May 26, 2025: Thanks to @neverbiasu for contributing ComfyUI.
• May 25, 2025: Special thanks to @LeanModels for providing the DF11-compressed version, and to @Gapeleon for the INT8-compressed version. We also appreciate @gluttony-10 for contributions to the Windows package.
• May 24, 2025: Together with @wangwei1237, @gluttony-10, and @KingNish24, we built a Gradio app and launched a Hugging Face Space.
• May 23, 2025: We have provided a training guideline in TRAIN.
• May 20, 2025: We released the official website, demo, model, and report for BAGEL.

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. 1.0 disables text guidance. Typical range: 4.0–8.0.
• cfg_image_scale: Controls how much the model preserves input image details. 1.0 disables 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. 1.0 disables 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: Like channel, but only applies to text condition (good for editing, may cause blur).
• If edited images appear blurry, try global CFG-Renorm, decrease cfg_renorm_min or decrease cfg_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.txt

2️⃣ 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.py

bash scripts/train.sh

You 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.

@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.