diff --git a/README.md b/README.md
index ca3e318..3330f2c 100644
--- a/README.md
+++ b/README.md
@@ -40,14 +40,14 @@ Our graphs show sequence lengths between 128 and 4096 (when standard attention r
 
 #### Speedup
 
-![FlashAttention speedup](images/flashattn_speedup.png)
+![FlashAttention speedup](images/flashattn_speedup.jpg)
 
 We generally see 2-4X speedup at sequence lengths between 128 and 4K, and we see more speedup when using dropout and masking, since we fuse the kernels.
 At sequence lengths that are popular with language models like 512 and 1K, we see speedups up to 4X when using dropout and masking.
 
 #### Memory
 
-![FlashAttention memory](images/flashattn_memory.png)
+![FlashAttention memory](images/flashattn_memory.jpg)
 
 We show memory savings in this graph (note that memory footprint is the same no matter if you use dropout or masking).
 Memory savings are proportional to sequence length -- since standard attention has memory quadratic in sequence length, whereas FlashAttention has memory linear in sequence length.
diff --git a/images/flashattn_memory.jpg b/images/flashattn_memory.jpg
new file mode 100644
index 0000000..d0b6b19
Binary files /dev/null and b/images/flashattn_memory.jpg differ
diff --git a/images/flashattn_memory.png b/images/flashattn_memory.png
deleted file mode 100644
index 42a82ec..0000000
Binary files a/images/flashattn_memory.png and /dev/null differ
diff --git a/images/flashattn_speedup.jpg b/images/flashattn_speedup.jpg
new file mode 100644
index 0000000..79fb4d5
Binary files /dev/null and b/images/flashattn_speedup.jpg differ
diff --git a/images/flashattn_speedup.png b/images/flashattn_speedup.png
deleted file mode 100644
index 3b1a895..0000000
Binary files a/images/flashattn_speedup.png and /dev/null differ