Update README.md

README.md

@@ -54,17 +54,8 @@ image = pipe(prompt, num_inference_steps=4, guidance_scale=0).images[0]
 The model was trained for 20k iterations on 2 H100 GPUs (representing approx. **13 hours** of training). Please refer to the [paper]() for further parameters details. 
 
 **Metrics on COCO 2017 validation set**
-
-- 2 steps:
-  - FID-5k: 22.6
-  - CLIP Score (ViT-g/14): 0.306
+- FID-5k: 22.6 (2 NFE) / 22.5 (4 NFE)
+- CLIP Score (ViT-g/14): 0.306 (2 NFE) / 
   
-- 4 steps:
-  - FID-5k: 22.5
-  - CLIP Score (ViT-g/14):
-
 **Metrics on COCO 2014 validation**
-- 2 steps:
-  - FID-30k:
-- 4 steps:
   - FID-30k: