Update README-en.md

README-en.md

@@ -61,7 +61,7 @@ The symbolic sequence listed next to the model is the hash value of the ckpt lis
 | --- | --- | --- | --- | --- |
 | DDD_pre1(d1ac03017b)  | Dreamlike Photoreal 1.0(f403e4e2a5) | 0.45,0.45,0.4,0.35,0.3,0.25,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 | 0 | DDD_pre2(601ec74593) |
 
-3. Fine-tuned DDD_pre2 using material images. The material images are output from other Stable Diffusion models.    
+3. Fine-tuned DDD_pre2 using [material images](https://huggingface.co/datasets/nakayama/DeDeDeDataset). The material images are output from other Stable Diffusion models.    
 The services/models used in the preparation were SD2.1, Novel AI, WD1.3/1.4, CoolJapan Diffusion 2.1, and Dreamlike Photoreal 2.0.    
 The total number of images is about 30,000. These were combined with flipped images and trained for 60000 steps at a learning rate of 5e-6.    
 The model generated by this process is DDD_pre3 (4709475652).