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-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Skywork/UniPic2-Metaquery-Flash with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Skywork/UniPic2-Metaquery-Flash", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,6 +35,7 @@ license: mit
|
|
| 35 |
|
| 36 |
**UniPic2-Metaquery-Flash** is a quantized variant of UniPic2-MetaQuery, offering end-to-end image understanding, text-to-image (T2I) generation, and image editing. Optimized for efficiency, it runs smoothly on NVIDIA RTX 40-series GPUs with under 16 GB VRAM — without any performance degradation.
|
| 37 |
<div align="center"> <img src="teaser.png" alt="Model Teaser" width="720"> </div>
|
|
|
|
| 38 |
|
| 39 |
|
| 40 |
## 📊 Benchmarks
|
|
|
|
| 35 |
|
| 36 |
**UniPic2-Metaquery-Flash** is a quantized variant of UniPic2-MetaQuery, offering end-to-end image understanding, text-to-image (T2I) generation, and image editing. Optimized for efficiency, it runs smoothly on NVIDIA RTX 40-series GPUs with under 16 GB VRAM — without any performance degradation.
|
| 37 |
<div align="center"> <img src="teaser.png" alt="Model Teaser" width="720"> </div>
|
| 38 |
+
<div align="center"> <img src="understanding.png" alt="Model Teaser" width="720"> </div>
|
| 39 |
|
| 40 |
|
| 41 |
## 📊 Benchmarks
|