Update README.md
Browse files
README.md
CHANGED
@@ -9,19 +9,16 @@ tags:
|
|
9 |
- art
|
10 |
- tensorRT
|
11 |
---
|
12 |
-
# Model Card for fast_sd_1.
|
13 |
|
14 |
-
fast_sd_1.
|
15 |
|
16 |
- weights: original stable diffusion 1.4 weights
|
17 |
-
- input image size range:
|
18 |
-
-
|
19 |
-
- super-resultion: 4x by default.
|
20 |
-
|
21 |
-
|
22 |
-
- depth(midas): yes
|
23 |
-
- xxx: yes
|
24 |
-
|
25 |
|
26 |
|
27 |
### Model Sources [optional]
|
@@ -30,32 +27,21 @@ fast_sd_1.4 is a tensorRT implementation of Stable diffusion model, with stable
|
|
30 |
|
31 |
## Uses
|
32 |
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
38 |
-
|
39 |
-
[More Information Needed]
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
### Recommendations
|
44 |
-
|
45 |
-
|
46 |
-
## How to Get Started with the Model
|
47 |
-
|
48 |
-
Use the code below to get started with the model.
|
49 |
|
50 |
-
[More Information Needed]
|
51 |
|
|
|
52 |
|
53 |
-
|
|
|
|
|
54 |
|
55 |
-
|
|
|
|
|
|
|
56 |
|
57 |
-
[More Information Needed]
|
58 |
|
59 |
-
## More Information [optional]
|
60 |
|
61 |
-
[More Information Needed]
|
|
|
9 |
- art
|
10 |
- tensorRT
|
11 |
---
|
12 |
+
# Model Card for fast_sd_1.5
|
13 |
|
14 |
+
fast_sd_1.5 is a tensorRT implementation of Stable diffusion model, with stable 1.5 weights. Main features
|
15 |
|
16 |
- weights: original stable diffusion 1.4 weights
|
17 |
+
- input image size range: 256~640 (min 256x256, max 640x640)
|
18 |
+
- device requirements: Nvidia Ampere architecture or newer (A100)
|
19 |
+
- super-resultion: 4x by default, optional.
|
20 |
+
|
21 |
+
fast_sd_1.5 is a part of TME lyralab Fast Model Plan.
|
|
|
|
|
|
|
22 |
|
23 |
|
24 |
### Model Sources [optional]
|
|
|
27 |
|
28 |
## Uses
|
29 |
|
30 |
+
```python
|
31 |
+
from fast_sd_1.5 import FSD
|
32 |
+
from PIL import Image
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
|
|
|
34 |
|
35 |
+
inference_model = FSD(plan="path/to/plan/dir", superres="4x")
|
36 |
|
37 |
+
# text input
|
38 |
+
text = "A red ballon flying in the sky"
|
39 |
+
output_img = inference_model.infer(text=text)
|
40 |
|
41 |
+
# img input
|
42 |
+
img = Image.open("test.jpg")
|
43 |
+
output_img = inference_model.infer(img=img)
|
44 |
+
```
|
45 |
|
|
|
46 |
|
|
|
47 |
|
|