| license: apache-2.0 | |
| datasets: | |
| - BLIP3o/BLIP3o-Pretrain-Long-Caption | |
| - BLIP3o/BLIP3o-Pretrain-Short-Caption | |
| - BLIP3o/BLIP3o-Pretrain-JourneyDB | |
| - UCSC-VLAA/GPT-Image-Edit-1.5M | |
| - BLIP3o/BLIP3o-60k | |
| - FreedomIntelligence/ShareGPT-4o-Image | |
| base_model: | |
| - OpenGVLab/InternVL3-1B | |
| This repository contains the model (1B version) presented in the paper UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing. | |
| UniLIP proposes a unified, CLIP-based encoder featuring both rich semantics and fine-grained image details. Through a **two-stage and self-distillation training** for reconstruction, we empower CLIP to achieve excellent reconstruction results **without compromising its original understanding abilities**. Leveraging this powerful unified representation, UniLIP excels across understanding, generation, and editing tasks. | |
| For more details, please refer to the original paper and the GitHub repository: | |
| Paper: https://www.arxiv.org/abs/2507.23278 | |
| GitHub: https://github.com/nnnth/UniLIP |