Add model card
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: diffusers
|
| 3 |
+
pipeline_tag: image-text-to-text
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
This repository contains the model described in the paper [Show-o Turbo: Towards Accelerated Unified Multimodal Understanding and Generation](https://arxiv.org/abs/2502.05415).
|
| 7 |
+
|
| 8 |
+
To get started with the 512-resolution model:
|
| 9 |
+
```bash
|
| 10 |
+
sh inference_t2i_512.sh
|
| 11 |
+
```
|
| 12 |
+
To get started with the 256-resolution model:
|
| 13 |
+
```bash
|
| 14 |
+
sh inference_t2i_256.sh
|
| 15 |
+
```
|