diff --git a/README.md b/README.md
index 662528c..99d88bb 100644
--- a/README.md
+++ b/README.md
@@ -9,10 +9,10 @@
 This is a fast, minimal implementation of Boris Dayma's [DALL·E Mega](https://github.com/borisdayma/dalle-mini).  It has been stripped down for inference and converted to PyTorch.  The only third party dependencies are numpy, requests, pillow and torch.
 
 To generate a 4x4 grid of DALL·E Mega images it takes
-- **1m 29s seconds** with a T4 in Colab
-- **48 seconds** with a P100 in Colab
-- **16 seconds** with an A100 on Replicate
-- **TBD** with an H100 (@NVIDIA?)
+- 89 sec with a T4 in Colab
+- 48 sec with a P100 in Colab
+- 16 sec with an A100 on Replicate
+- TBD with an H100 (@NVIDIA?)
 
 The flax model and code for converting it to torch can be found [here](https://github.com/kuprel/min-dalle-flax).
 
diff --git a/setup.py b/setup.py
index f5510ab..fdbaa98 100644
--- a/setup.py
+++ b/setup.py
@@ -5,7 +5,7 @@ setuptools.setup(
     name='min-dalle',
     description = 'min(DALL·E)',
     long_description=(Path(__file__).parent / "README.rst").read_text(),
-    version='0.2.16',
+    version='0.2.17',
     author='Brett Kuprel',
     author_email='brkuprel@gmail.com',
     url='https://github.com/kuprel/min-dalle',