Add link to paper

This PR adds a link to the paper [When does training on downscaled images yield the same gradients?](https://huggingface.co/papers/2608.04448) to the model card.

README.md

@@ -1,11 +1,13 @@
 ---
-license: apache-2.0
 base_model:
 - circlestone-labs/Anima
+license: apache-2.0
 pipeline_tag: text-to-image
 ---
 
-[Anima](https://huggingface.co/circlestone-labs/Anima) lora for turbo generation, implemented with [DP-DMD](https://arxiv.org/abs/2602.03139) and Continuous-Time Distillation [paper](https://arxiv.org/abs/2605.06376)
+[Anima](https://huggingface.co/circlestone-labs/Anima) lora for turbo generation, implemented with [DP-DMD](https://arxiv.org/abs/2602.03139) and Continuous-Time Distillation [paper](https://arxiv.org/abs/2605.06376).
+
+This model is presented in the paper [When does training on downscaled images yield the same gradients?](https://huggingface.co/papers/2608.04448).
 
 Try new `anima_turbo_4step_v2_longer.safetensors`