JUICE-2B-SigLIP2-Base

Pretrained model (stage 1). It is the starting point of the SFT.

JUICE is one flow-matching Transformer (MM-RiT d28, 2.1 B parameters) that generates images and text together in the representation spaces of frozen encoders: SigLIP2 patch states for images and Flan-T5-Small token states for text.

• Code: https://github.com/Ced3-han/JUICE-Code
• Paper: https://arxiv.org/abs/2610.28801
• All JUICE models: https://huggingface.co/collections/CedLJH/juice
• Weights: fast EMA weights (decay 0.9996) at step 60,000 of the pretraining.
• Image space: siglip2; inference defaults of the paper in config.json.

Usage

Install the code from https://github.com/Ced3-han/JUICE-Code, then:

from juice.pipeline import JuicePipeline

pipe = JuicePipeline.from_pretrained("CedLJH/JUICE-2B-SigLIP2-Base", device="cuda")
images = pipe.text_to_image("a red bicycle next to a blue door", num_images=4, seed=0)
answers = pipe.answer(["photo.jpg"], ["What color is the door?"])

License

The weights are under CC BY-NC 4.0. The code downloads the frozen encoders and decoders separately; they keep their own licenses (see THIRD_PARTY_LICENSES.md in the code repository).

Citation

@article{li2026juice,
  title   = {{JUICE}: Unified Multimodal Modeling in Pretrained Representation Spaces},
  author  = {Li, Jiahan and Su, Huangyuan and Tong, Shengbang and Yang, Shusheng and
             Guo, Ruihan and Huang, Suozhi and Zhao, Hexu and Sharma, Pratyusha and
             Yang, Sherry and Gu, Jiatao and Fergus, Rob and Cho, Kyunghyun},
  journal = {arXiv preprint arXiv:2610.28801},
  year    = {2026}
}