Update README.md
Browse files
README.md
CHANGED
|
@@ -48,8 +48,14 @@ widget:
|
|
| 48 |
|
| 49 |
### review
|
| 50 |
- should set the output image size according to the model stated, i.e., 1024x1024 or 512x512
|
|
|
|
| 51 |
- small size model but good quality pictures; support image-to-image, image-text-to-image; and t5 encoder allows you to input short description or sentence instead of tag(s)
|
| 52 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
### **reference**
|
| 55 |
- base model from [pixart-alpha](https://huggingface.co/PixArt-alpha)
|
|
|
|
| 48 |
|
| 49 |
### review
|
| 50 |
- should set the output image size according to the model stated, i.e., 1024x1024 or 512x512
|
| 51 |
+
- pixart-xl-2-1024-ms is recommended (with 1024x1024 size)
|
| 52 |
- small size model but good quality pictures; support image-to-image, image-text-to-image; and t5 encoder allows you to input short description or sentence instead of tag(s)
|
| 53 |
+
- more quantized versions of t5xxl encoder can be found [here](https://huggingface.co/chatpig/t5xxl/tree/main)
|
| 54 |
+
- upgrade your gguf-node (see the last item in reference below) to the latest version for pixart model support
|
| 55 |
+
|
| 56 |
+
### **paper**
|
| 57 |
+
- [pixart-α](https://arxiv.org/pdf/2310.00426)
|
| 58 |
+
- [high-resolution image synthesis](https://arxiv.org/pdf/2112.10752)
|
| 59 |
|
| 60 |
### **reference**
|
| 61 |
- base model from [pixart-alpha](https://huggingface.co/PixArt-alpha)
|