Update README.md

README.md

@@ -9,6 +9,7 @@ library_name: diffusers
 pipeline_tag: text-to-image
 language:
 - en
+new_version: 8BitStudio/Aniimage-2
 ---
 
 ![Aniimage-1 Samples](collage.png)
@@ -117,10 +118,14 @@ When using plain English text, you are much less likely to experience this issue
 
 ## What's Next
 
-**Aniimage-1.5** Was a fine-tune of Aniimage-1 but was not released due to its quality not being much better than 1.0.
+**[Aniimage-2](https://huggingface.co/8BitStudio/Aniimage-2) is complete!**
+
+It features a native resolution of 512×512 and was trained on 1.2 million unique images, compared with the 830,000 images used to train Aniimage-1.
+
+Aniimage-2 also switches from Aniimage-1’s epsilon-prediction objective to v-prediction and uses a zero-terminal signal-to-noise ratio. 
+It also uses uniform timestep sampling, while the upcoming Aniimage-3 will adopt logit-normal noise-level sampling as part of its flow-matching objective.
+
 
-Aniimage-2.0 is currently training and will be done soon. 2.0 has many features including quality filters for dataset images, 512x512 native image training, and architecture changes.
-Due to Aniimage-2.0 having a better VAE and being at 512x512 natively, pupils and hands should look significantly better.
 
 ## License