English
art
Stable Diffusion
benleader commited on
Commit
d1e7766
1 Parent(s): e9a576f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -5
README.md CHANGED
@@ -8,19 +8,21 @@ tags:
8
  ---
9
  ## Model Card for lyraSD
10
 
11
- lyraSD is currently the **fastest Stable Diffusion model** that can 100% align the outputs of **diffusers** available, boasting an inference cost of only **0.52 seconds** for a 512x512 image, accelerating the process up to **80% faster** than the original version.
 
 
12
 
13
  Among its main features are:
14
 
 
 
 
15
  - 4 Commonly used Pipelines
16
  - - Text2Img
17
  - - Img2Img
18
  - - ControlNetText2Img
19
  - - ControlNetImg2Img
20
- - 100% likeness to diffusers output
21
- - ControlNet Hot Swap: Can hot swap a ControlNet model weights within 0.4s (0s if cached)
22
- - Lora How Swap: Can hot swap a Lora within 0.5s (0.1s if cached)
23
- - device requirements: Nvidia Ampere architecture (A100, A10) or compatable
24
 
25
  ## Speed
26
 
 
8
  ---
9
  ## Model Card for lyraSD
10
 
11
+ We consider the Diffusers as the much more extendable framework for the SD ecosystem. Therefore, we have made a pivot to Diffusers, leading to a complete update of lyraSD.
12
+
13
+ lyraSD is currently the **fastest Stable Diffusion model** that can 100% align the outputs of **Diffusers** available, boasting an inference cost of only **0.52 seconds** for a 512x512 image, accelerating the process up to **80% faster** than the original version.
14
 
15
  Among its main features are:
16
 
17
+ - **ControlNet Hot Swap**: Can hot swap a ControlNet model weights within 0.4s (0s if cached)
18
+ - **Lora How Swap**: Can hot swap a Lora within 0.5s (0.1s if cached)
19
+ - 100% likeness to diffusers output
20
  - 4 Commonly used Pipelines
21
  - - Text2Img
22
  - - Img2Img
23
  - - ControlNetText2Img
24
  - - ControlNetImg2Img
25
+ - Device requirements: Nvidia Ampere architecture (A100, A10) or compatable
 
 
 
26
 
27
  ## Speed
28