Update README.md

README.md

@@ -2,7 +2,7 @@
 license: openrail++
 ---
 
-# Terminus XL Gamma
+# Terminus XL Gamma (v2 preview)
 
 ## Model Details
 
@@ -10,13 +10,14 @@ license: openrail++
 
 Terminus XL Gamma is a new state-of-the-art latent diffusion model that uses zero-terminal SNR noise schedule and velocity prediction objective at training and inference time.
 
-Terminus is based on the same architecture as SDXL, and has the same layout. It has been trained on fewer steps with very high quality data captions via COCO and Midjourney.
+Terminus is based on a similar architecture to SDXL, and has the same layout. It has been trained on fewer steps with very high quality data captions via COCO and Midjourney.
 
 This model will not be capable of as many concepts as SDXL, and some subjects will simply look very bad.
 
-The objective of this model was to use min-SNR gamma loss to efficiently train a full model on a single A100-80G.
+The objective of this model was to use v-prediction and min-SNR gamma loss to efficiently train a full zero-terminal SNR model on a single A100-80G.
 
 
+- **Fine-tuned from:** ptx0/terminus-xl-gamma-v1
 - **Developed by:** pseudoterminal X (@bghira)
 - **Funded by:** pseudoterminal X (@bghira)
 - **Model type:** Latent Diffusion
@@ -64,11 +65,13 @@ This model's success largely depended on a somewhat small collection of very hig
 
 #### Preprocessing
 
-Followed SDXL's pretraining procedure using crop conditional inputs and centre-cropped images with their full size as the input.
+Most of the existing process for terminus-xl-gamma-v1 was followed, with the exception of training extensively on cropped images using SDXL's crop coordinates to improve fine details.
 
-Trained on 512x512, followed by 768x768, and finally, ~1 megapixel multi-aspect training for the rest of the training time.
+No images were upsampled during this training session. Images were downsampled using LANCZOS instead of BICUBIC filters to attain higher image fidelity and maintain more image context for the model to learn from.
 
-Images were downsampled while maintaining aspect ratio and cropped on 64 pixel increments. Many aspect ratios were trained, but only a few are likely to work fully.
+Only high-quality photos were used in this training session, greatly improving the realism qualities.
+
+~770,000 images were used for this training run.
 
 #### Training Hyperparameters