Any-to-Any
Transformers
Diffusers
Safetensors
text-to-image
image-editing
image-understanding
vision-language
multimodal
autoregressive
unified-model
Instructions to use Skywork/UniPic2-Metaquery-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Skywork/UniPic2-Metaquery-9B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Skywork/UniPic2-Metaquery-9B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
关于Benchmark评测结果
#3
by Rebelliousgang - opened
请问Model Card这里的评测结果是使用OpenAI 评测的么,是应该与Table1中的最下面一行做对比么?
UniPic2-Metaquery-9B w/o GRPO achieves competitive results across a variety of vision-language tasks:
Task Score
🧠 GenEval 0.86
🖼️ DPG-Bench 83.63
✂️ GEditBench-EN 6.90
🧪 ImgEdit-Bench 4.10
是的