| pipeline_tag: image-to-image | |
| tags: | |
| - pytorch | |
| - super-resolution | |
| **PURE** is the first framework to employ a multimodal large language model (MLLM) as its backbone for addressing low-level vision tasks. | |
| [](https://arxiv.org/abs/2503.11073) | |
| # Usage | |
| We provide the implementation of PURE, as well as sampling code, in our [github repository](https://github.com/nonwhy/PURE/). |