Update README.md

README.md

@@ -31,7 +31,7 @@ It is not based on any existing models, the UNet is trained from scratch.
 | **Dataset** | ~1.2 million curated anime images from Danbooru |
 | **GPU** | NVIDIA RTX 5060 Ti 16GB |
 | **Scheduler** | DPM++ SDE |
-| **Step count** | 50 using DPM++ SDE|
+| **Recommended steps** | 50|
 
 ## Requirements
 
@@ -142,10 +142,10 @@ The model generates male characters less reliably than female characters, it may
 
 ## What's Next
 
-Aniimage-3 is currently in the works and will have a much higher parameter count: 738.1M parameters compared to Aniimage-2 and Aniimage-1's 433.4M parameters.
+Aniimage-2.5 is currently in the works and will have a much higher parameter count: 738.1M parameters compared to Aniimage-2 and Aniimage-1's 433.4M parameters.
 The model will also have significantly more unique images.
 Aniimage-2 used incorrect Min-SNR loss weighting with its v-prediction objective, causing near-pure-noise timesteps to receive excessive emphasis. This has been corrected for Aniimage-3.
-Aniimage-3 also uses a much higher-quality dataset with improved filtering. More than 100,000 low-quality images from the Aniimage-2 dataset were removed.
+Aniimage-2.5 also uses a much higher-quality dataset with improved filtering. More than 100,000 low-quality images from the Aniimage-2 dataset were removed.
 
 
 ## License