---
license: llama2
language:
- en
base_model:
- lmsys/vicuna-7b-v1.5
- liuhaotian/llava-v1.5-7b-lora
- stable-diffusion-v1-5/stable-diffusion-v1-5
pipeline_tag: image-text-to-text
---

# DiffLMM Model Card

## Model details

**Model type:**
DiffLMM is a multimodal model built based on [LLaVA](https://github.com/haotian-liu/LLaVA) and [Stable Diffusion](https://github.com/CompVis/stable-diffusion) with enhanced grounding ability and preserved conversation ability.

**Paper or resources for more information:**
https://groundlmm.github.io/

**Where to send questions or comments about the model:**
https://github.com/Shengcao-Cao/groundLMM

## License
Llama 2 is licensed under the LLAMA 2 Community License, 
Copyright (c) Meta Platforms, Inc. All Rights Reserved.