Create README.md

README.md

@@ -0,0 +1,37 @@
+---
+license: other
+license_name: nvidia-open-model-license
+license_link: >-
+  https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license
+library_name: cosmos
+tags:
+- cosmos
+base_model:
+- nebulette/cozyberry-g4-vision
+---
+
+C/B-SIDE
+
+A diffusion model with BERT. It's backward compatible with the T5 tokenizer.
+
+Spatial encoding loss was calculated as [it was explained elsewhere](https://huggingface.co/nebulette/fashion-side).
+
+![](images/couple.png)
+
+Cozyberry was chosen as the only text encoder. There are no adapters.
+
+As in the [waifu diffusion](https://ruwwww.github.io/al-folio/blog/2026/waifu-diffusion/), the image output alignment requires 10-100x less VRAM, due to the use of random patch cropping during training.
+
+![](images/crop.png)
+
+History
+
+- After two months of work, 20 version updates, and evaluating 5 different text encoders...
+- The final lightweight [BERT model](https://huggingface.co/nebulette/rnberry) was born
+- Later on, thousands of styles from the danbooru 2025-26 were extracted, and the model learned from both [the textual and visual clues](https://huggingface.co/nebulette/cozyberry-g4-vision)
+- In this release, horizontal scenes were further reinforced exclusively for the BERT model
+
+Source data
+
+- synthetic booru character fashion
+- horizontal scenes