Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@
|
|
| 10 |
|
| 11 |
<sup>1</sup> [Show Lab](https://sites.google.com/view/showlab/home?authuser=0), National University of Singapore <sup>2</sup> Bytedance
|
| 12 |
|
| 13 |
-
[](https://github.com/showlab/Show-o/blob/main/show-o2/Show_o2.pdf) [](https://github.com/showlab/Show-o/blob/main/docs/wechat_qa_3.jpg)
|
| 14 |
</div>
|
| 15 |
|
| 16 |
## What is the new about Show-o2?
|
|
@@ -20,7 +20,7 @@ We perform the unified learning of multimodal understanding and generation on th
|
|
| 20 |
## Pre-trained Model Weigths
|
| 21 |
The Show-o2 checkpoints can be found on Hugging Face:
|
| 22 |
* [showlab/show-o2-1.5B](https://huggingface.co/showlab/show-o2-1.5B)
|
| 23 |
-
* [showlab/show-o2-1.5B-HQ](https://huggingface.co/showlab/show-o2-1.5B)
|
| 24 |
* [showlab/show-o2-7B](https://huggingface.co/showlab/show-o2-7B)
|
| 25 |
|
| 26 |
## Getting Started
|
|
@@ -46,9 +46,14 @@ python3 inference_mmu.py config=configs/showo2_7b_demo_432x432.yaml \
|
|
| 46 |
mmu_image_path=./docs/mmu/pexels-taryn-elliott-4144459.jpg question='How many avocados (including the halved) are in this image? Tell me how to make an avocado milkshake in detail.'
|
| 47 |
```
|
| 48 |
|
| 49 |
-
|
| 50 |
Demo for **Text-to-Image Generation** and you can find the results on wandb.
|
| 51 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
python3 inference_t2i.py config=configs/showo2_1.5b_demo_432x432.yaml \
|
| 53 |
batch_size=4 guidance_scale=7.5 num_inference_steps=50;
|
| 54 |
|
|
@@ -56,8 +61,6 @@ python3 inference_t2i.py config=configs/showo2_7b_demo_432x432.yaml \
|
|
| 56 |
batch_size=4 guidance_scale=7.5 num_inference_steps=50;
|
| 57 |
```
|
| 58 |
|
| 59 |
-
|
| 60 |
-
|
| 61 |
### Citation
|
| 62 |
To cite the paper and model, please use the below:
|
| 63 |
```
|
|
|
|
| 10 |
|
| 11 |
<sup>1</sup> [Show Lab](https://sites.google.com/view/showlab/home?authuser=0), National University of Singapore <sup>2</sup> Bytedance
|
| 12 |
|
| 13 |
+
[](https://github.com/showlab/Show-o/blob/main/show-o2/Show_o2.pdf) [](https://github.com/showlab/Show-o/blob/main/docs/wechat_qa_3.jpg)
|
| 14 |
</div>
|
| 15 |
|
| 16 |
## What is the new about Show-o2?
|
|
|
|
| 20 |
## Pre-trained Model Weigths
|
| 21 |
The Show-o2 checkpoints can be found on Hugging Face:
|
| 22 |
* [showlab/show-o2-1.5B](https://huggingface.co/showlab/show-o2-1.5B)
|
| 23 |
+
* [showlab/show-o2-1.5B-HQ](https://huggingface.co/showlab/show-o2-1.5B-HQ)
|
| 24 |
* [showlab/show-o2-7B](https://huggingface.co/showlab/show-o2-7B)
|
| 25 |
|
| 26 |
## Getting Started
|
|
|
|
| 46 |
mmu_image_path=./docs/mmu/pexels-taryn-elliott-4144459.jpg question='How many avocados (including the halved) are in this image? Tell me how to make an avocado milkshake in detail.'
|
| 47 |
```
|
| 48 |
|
|
|
|
| 49 |
Demo for **Text-to-Image Generation** and you can find the results on wandb.
|
| 50 |
```
|
| 51 |
+
python3 inference_t2i.py config=configs/showo2_1.5b_demo_1024x1024.yaml \
|
| 52 |
+
batch_size=4 guidance_scale=7.5 num_inference_steps=50;
|
| 53 |
+
|
| 54 |
+
python3 inference_t2i.py config=configs/showo2_1.5b_demo_512x512.yaml \
|
| 55 |
+
batch_size=4 guidance_scale=7.5 num_inference_steps=50;
|
| 56 |
+
|
| 57 |
python3 inference_t2i.py config=configs/showo2_1.5b_demo_432x432.yaml \
|
| 58 |
batch_size=4 guidance_scale=7.5 num_inference_steps=50;
|
| 59 |
|
|
|
|
| 61 |
batch_size=4 guidance_scale=7.5 num_inference_steps=50;
|
| 62 |
```
|
| 63 |
|
|
|
|
|
|
|
| 64 |
### Citation
|
| 65 |
To cite the paper and model, please use the below:
|
| 66 |
```
|