Figured out actual difference between Consistency tests.

README.md

@@ -15,14 +15,18 @@ tags:
     
   (So `loss_total = flow matching + 0.1 * latent_perceptual_loss`).  I only did this if the timestep was less than 50% (`sigmas < 0.5`).
   
-  ## **Loras/RF-Flux2VAE-Consistency-Test-50-000002.safetensors**
+  ## **Loras/RF-Flux2VAE-Consistency-Test-000002.safetensors**
   
-  trained by generating one forward pass from 20-50 timestep before the target timestep with **no gradients**. Then simulating one euler step to the target timestep and using the resulting latent as the input to the model and training on that. So the model is trained on `clean latent + noise + discretization error + mispredicition error from previous step`
+  Trained by generating one forward pass from 20-30 timesteps before the target timestep with **no gradients**. Then simulating one euler step to the target timestep and using the resulting latent as the input to the model and training on that. So the model is trained on `clean latent + noise + discretization error + mispredicition error from previous step`
   
   My thinking was at inference time the model **doesn't** only receive the `clean latent + gaussian noise` like in training, but also `+ discretization error + mispredicition error from previous step`
   
   Works on [Mugen](https://huggingface.co/CabalResearch/Mugen) too, but trained on [NoobAI-Flux2VAE-RectifiedFlow-0.3](https://huggingface.co/CabalResearch/NoobAI-Flux2VAE-RectifiedFlow-0.3)
+
+  The one below performs **better** 
   
-  ## **Loras/RF-Flux2VAE-Consistency-Test-000002.safetensors**
-  
-  Same as above, with bigger but worse dataset. Use the above one (the one with 50 in the name) generally. 
+  ## **Loras/RF-Flux2VAE-Consistency-Test-50-000002.safetensors**
+
+  Same exact settings as above, but trained using timestep jumps of 50-60.
+
+  Performs **better**