Incorporo-user commited on
Commit
936aea5
·
verified ·
1 Parent(s): ebfded8

README: speed line

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -31,7 +31,7 @@ and the TAESD decoder all run on your own GPU through WebGPU (onnxruntime-web).
31
 
32
  ## Speed and accuracy
33
 
34
- - About 6–8 s per 50-step 256×256 image on an RTX 4060, after roughly 10 s of one-time model
35
  setup per visit.
36
  - With identical initial noise, the browser output matches the PyTorch reference pipeline within 5/255
37
  per pixel (run the self-test with `?parity=1`).
 
31
 
32
  ## Speed and accuracy
33
 
34
+ - About 6–7 s per 50-step 256×256 image on an RTX 4060, after roughly 10 s of one-time model
35
  setup per visit.
36
  - With identical initial noise, the browser output matches the PyTorch reference pipeline within 5/255
37
  per pixel (run the self-test with `?parity=1`).