Update README.md

README.md

@@ -6,11 +6,14 @@ language:
 - en
 pipeline_tag: text-to-image
 ---
-Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation (https://huggingface.co/papers/2402.10210)
+**Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation** (https://huggingface.co/papers/2402.10210)
 
-# SPIN-Diffusion-iter1
 
-This model is a self-play fine-tuned diffusion model at iteration 2 from [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) using synthetic data based on on the [yuvalkirstain/pickapic_v2](https://huggingface.co/datasets/yuvalkirstain/pickapic_v2) dataset.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/657be24e8d360b690d5b665f/uzhoFO22ZdQ5XjBxxDA1a.png)
+
+# SPIN-Diffusion-iter2
+
+This model is a self-play fine-tuned diffusion model at iteration 2 from [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) using synthetic data based on the winner images of the [yuvalkirstain/pickapic_v2](https://huggingface.co/datasets/yuvalkirstain/pickapic_v2) dataset.
 
 ## Model Details
 
@@ -30,7 +33,7 @@ The following hyperparameters were used during training:
 - num_devices: 8
 - train_gradient_accumulation_steps: 32
 - total_train_batch_size: 2048
-- optimizer: AdamW
+- optimizer: AdamW 
 - lr_scheduler: "linear"
 - lr_warmup_steps: 200
 - num_training_steps: 500