Update README.md

README.md

@@ -37,8 +37,10 @@ pip install transformers accelerate safetensors
 ```
 
 **Notes:**
-- The pipeline uses the `EDMEulerScheduler` scheduler by default. It's an [EDM formulation](https://arxiv.org/abs/2206.00364) of the Euler scheduler. `guidance_scale=5.0` is a good default for this scheduler.
-- The pipeline also supports the `EDMDPMSolverMultistepScheduler` scheduler, for crisper fine details. It's an [EDM formulation](https://arxiv.org/abs/2206.00364) of the DPM scheduler. `guidance_scale=3.0` is a good default for this scheduler.
+- The pipeline uses the `EDMEulerScheduler` scheduler. It's an [EDM formulation](https://arxiv.org/abs/2206.00364) of the Euler scheduler.
+- `guidance_scale=5.0` is a good default for this scheduler.
+- The pipeline also supports the `EDMDPMSolverMultistepScheduler` scheduler.  It's an [EDM formulation](https://arxiv.org/abs/2206.00364) of the DPM scheduler.
+- `guidance_scale=3.0` is a good default for this scheduler.
 
 Then, run the following snippet:
 
@@ -66,21 +68,27 @@ This model card only provides a brief summary of our user study results. For ext
 
 We conducted studies to measure overall aesthetic quality, as well as for the specific areas we aimed to improve with Playground v2.5, namely multi aspect ratios and human preference alignment.
 
-The aesthetic quality of Playground v2.5 dramatically outperforms the current state-of-the-art open source models SDXL and PIXART-α, as well as Playground v2. Because the performance differential between Playground V2.5 and SDXL was so large, we also tested our aesthetic quality against world-class closed-source models like DALL-E 3 and Midjourney 5.2, and found that Playground v2.5 outperforms them as well.
+#### Compare to state-of-the-art
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63855d851769b7c4b10e1f76/V7LFNzgoQJnL__ndU0CnE.png)
 
-Similarly, for multi aspect ratios, we outperform SDXL by a large margin.
+The aesthetic quality of Playground v2.5 dramatically outperforms the current state-of-the-art open source models SDXL and PIXART-α, as well as Playground v2. Because the performance differential between Playground V2.5 and SDXL was so large, we also tested our aesthetic quality against world-class closed-source models like DALL-E 3 and Midjourney 5.2, and found that Playground v2.5 outperforms them as well.
+
+#### Multi-aspect Ratios
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/636c0c4eaae2da3c76b8a9a3/xMB0r-CmR3N6dABFlcV71.png)
 
-Next, we benchmark Playground v2.5 specifically on people-related images, to test Human Preference Alignment. We compared Playground v2.5 against two commonly-used baseline models: SDXL and RealStock v2, a community fine-tune of SDXL that was trained on a realistic people dataset.
+Similarly, for multi aspect ratios, we outperform SDXL by a large margin.
 
-Playground v2.5 outperforms both baselines by a large margin.
+#### Human-centric Study
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/636c0c4eaae2da3c76b8a9a3/7c-8Stw52OsNtUjse8Slv.png)
 
-### MJHQ-30K benchmark
+Next, we benchmark Playground v2.5 specifically on people-related images, to test Human Preference Alignment. We compared Playground v2.5 against two commonly-used baseline models: SDXL and RealStock v2, a community fine-tune of SDXL that was trained on a realistic people dataset.
+
+Playground v2.5 outperforms both baselines by a large margin.
+
+### MJHQ-30K Benchmark
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/636c0c4eaae2da3c76b8a9a3/7tyYDPGUtokh-k18XDSte.png)