Update model card
Browse files
README.md
CHANGED
|
@@ -11,16 +11,14 @@ tags:
|
|
| 11 |
---
|
| 12 |
## Model Card for lyraSD
|
| 13 |
|
| 14 |
-
lyraSD is
|
| 15 |
|
| 16 |
-
- weights: original stable diffusion 1.
|
| 17 |
- input image: 512x512 (in img2img mode)
|
| 18 |
- output image: 512x512
|
| 19 |
- device requirements: Nvidia Ampere architecture (A100) or compatable
|
| 20 |
- super-resultion: 4x by default, optional.
|
| 21 |
|
| 22 |
-
lyraSD is a part of TME lyralab Fast Model Plan.
|
| 23 |
-
|
| 24 |
## Speed
|
| 25 |
|
| 26 |
### test on A100, img size: 512x512,superresolution=False, mode=text2img
|
|
|
|
| 11 |
---
|
| 12 |
## Model Card for lyraSD
|
| 13 |
|
| 14 |
+
lyraSD is currently the fastest Stable Diffusion model available, boasting an inference cost of only 0.36 seconds for a 512x512 image, accelerating the process up to 10 times faster than the original version. Among its main features are:
|
| 15 |
|
| 16 |
+
- weights: original stable diffusion 1.4 weights
|
| 17 |
- input image: 512x512 (in img2img mode)
|
| 18 |
- output image: 512x512
|
| 19 |
- device requirements: Nvidia Ampere architecture (A100) or compatable
|
| 20 |
- super-resultion: 4x by default, optional.
|
| 21 |
|
|
|
|
|
|
|
| 22 |
## Speed
|
| 23 |
|
| 24 |
### test on A100, img size: 512x512,superresolution=False, mode=text2img
|