Text-to-Image
Diffusers
vladmandic commited on
Commit
433700d
·
1 Parent(s): ad7a32e

update readme

Browse files

Signed-off-by: Vladimir Mandic <mandic00@live.com>

Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,7 +6,7 @@ library_name: diffusers
6
 
7
  # MicroDecoder
8
 
9
- **MicroDecoder** VAE can be trained on *any* diffusion model in **~15min** and provides low-quality reconstruction from latents to RGB in **~0.01sec**.
10
 
11
  Inference includes noise correction based on current timestep, blurring corrections plus upscale interpolation: all with intention of providing as fast-as-possible reconstruction that is viable and consistent with any noise levels.
12
 
 
6
 
7
  # MicroDecoder
8
 
9
+ **MicroDecoder** VAE can be trained on *any* diffusion model in **~5-15min** and provides low-quality reconstruction from latents to RGB in **~0.01sec**.
10
 
11
  Inference includes noise correction based on current timestep, blurring corrections plus upscale interpolation: all with intention of providing as fast-as-possible reconstruction that is viable and consistent with any noise levels.
12