Update README.md

README.md

@@ -38,7 +38,7 @@ Such strong conditions make our model less likely to be affected.
 **Training Data**
 The model developer used the following dataset for training the model:
 
-- Our model is finetuned on [LSDIR](https://data.vision.ee.ethz.ch/yawli/index.html) + 100K samples from FFHQ datasets.
+- Our model is finetuned on [LSDIR](https://data.vision.ee.ethz.ch/yawli/index.html) + 10K samples from FFHQ datasets.
 
 **Training Procedure**
 S3Diff is an image super-resolution model finetuned on [SD-Turbo](https://huggingface.co/stabilityai/sd-turbo), further equipped with a degradation-guided LoRA and online negative prompting.