Update README.md

README.md

@@ -40,3 +40,25 @@ You should then be able to do the typical diffusers code. For example:
       print(f"saving to {fname}")
       image.save(fname)
 
+
+# Making your own FlowMatch model
+
+Doing the training itself, did not take that long.
+Writing my own, functional training code, and trying various pathways to find what works, took WEEKS.
+
+If you wanted to recreate your own from scratch, here's the details from one of my runs:
+(This only takes a few hours to complete, on a 4090)
+
+(Batchsize 40, accum=1 for all)
+
+* time blocks only, 1e-5, 350 steps (result very murky here, thats expected)
+* up.0 and up.1, 1e-6, 75 steps
+* mid, 1e-6, 60 steps
+* up.2, 1e-6, 160 steps
+* up.3, 1e-6, 120 steps
+
+## Sampling
+During the first phase, maybe sample every 50 steps.
+After the first phase, you'll want to take samples every 10 steps. Make sure you use MULTIPLE samples,
+and ideally of different types. You should have at least one "single token" prompt, and then a few more
+complex ones.