Update README.md (#1)

- Update README.md (8b5a2b0b11415ee643df4485b88a6b360fdbcecb)


Co-authored-by: Onur <[email protected]>

README.md

@@ -11,8 +11,7 @@ inference: False
 ---
 # ⚡ FlashDiffusion: FlashSD ⚡
 
-
-Flash Diffusion is a diffusion distillation method proposed in [ADD ARXIV]() *by Clément Chadebec, Onur Tasar and Benjamin Aubin.*
+Flash Diffusion is a diffusion distillation method proposed in [ADD ARXIV]() *by Clément Chadebec, Onur Tasar, Eyal Benaroche, and Benjamin Aubin.*
 This model is a **26.4M** LoRA distilled version of SD1.5 model that is able to generate images in **2-4 steps**. The main purpose of this model is to reproduce the main results of the paper.
 
 
@@ -54,14 +53,16 @@ image = pipe(prompt, num_inference_steps=4, guidance_scale=0).images[0]
 </p>
 
 # Training Details
-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. 
+The model was trained for 20k iterations on 2 H100 GPUs (representing approx. **26 hours** of training). Please refer to the [paper]() for further parameters details. 
 
-**Metrics on COCO 2017 validation set**
+**Metrics on COCO 2017 validation set (Table 1)**
 - FID-5k: 22.6 (2 NFE) / 22.5 (4 NFE)
 - CLIP Score (ViT-g/14): 0.306 (2 NFE) / 0.311 (4 NFE)
   
-**Metrics on COCO 2014 validation**
+**Metrics on COCO 2014 validation (Table 2)**
+  - FID-30k: 12.41 (4 NFE)
   - FID-30k: 12.07 (2 NFE)
 
+
 ## License
 This model is released under the the Creative Commons BY-NC license.