Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,25 @@
+---
+license: apache-2.0
+tags:
+- ddpo
+- stable-diffusion
+- reinforcement-learning
+- lora
+---
+
+# DDPO Sharpness Checkpoints
+
+LoRA checkpoints from DDPO fine-tuning of Stable Diffusion v1.4 with a sharpness reward (Laplacian variance).
+
+## Training Details
+
+- Base model: CompVis/stable-diffusion-v1-4
+- Method: DDPO with LoRA
+- Reward: Sharpness (Laplacian variance)
+- Prompts: ImageNet animals
+- Epochs: 100
+- Compute: 4x A100-SXM4-80GB (MIT ORCD)
+
+## Checkpoints
+
+Uploaded every 10 epochs: checkpoint_0, checkpoint_10, ..., checkpoint_90, checkpoint_98 (final).