Update README.md

README.md

@@ -7,20 +7,16 @@ tags:
 pipeline_tag: text-to-image
 ---
 
-Here's a draft for your **Skittles v2** model card on Hugging Face:
-
----
-
 # Skittles v2
 
 ## Model Summary
 
-**Skittles v2** is a cutting-edge text-to-image generation model, created by merging components from the **FLUX.1 Schnell** architecture. By combining the precision of **FLUX.1 Schnell** with advanced tweaks, **Skittles v2** is designed to offer high-quality image outputs comparable to **FLUX.1 Dev** while maintaining a streamlined configuration for efficient inference.
+**Skittles v2** is a cutting-edge text-to-image generation model, created by merging components from the **FLUX.1 Schnell** architecture. By combining the precision of **FLUX.1 Schnell** with advanced tweaks, **Skittles v2** is designed to offer high-quality image outputs.
 
 - **Type**: Text-to-Image Generation
 - **Architecture**: Merged FLUX.1 Schnell with CFG capabilities
-- **Output Quality**: On par with **FLUX.1 Dev**
-- **Performance**: Optimized for both speed and image fidelity
+- **Output Quality**: Seems to be on par with **FLUX.1 Dev**
+- **Performance**: Optimized for both image fidelity (speed is degraded (I'm looking into it))
 
 ---
 
@@ -28,7 +24,6 @@ Here's a draft for your **Skittles v2** model card on Hugging Face:
 
 - **CFG Integration**: Skittles v2 unlocks CFG (Classifier-Free Guidance) capabilities, offering fine-grained control over image generation.
 - **High Fidelity**: Produces ultra-realistic and detailed images.
-- **Optimized Performance**: Merged architecture reduces latency during inference while retaining quality.
 - **Customizable Output**: Supports a wide range of prompts, styles, and configurations.
 
 ---
@@ -39,7 +34,6 @@ Here's a draft for your **Skittles v2** model card on Hugging Face:
 - **Merge Approach**: The model was combined using a custom merging strategy, blending FLUX.1 Schnell’s architecture with optimized CFG decoding.
 - **Training Paradigm**: Not retrained, but restructured for improved inference performance.
 - **Output Size**: Supports resolutions up to 1024x1024 pixels.
-- **Quantization Compatibility**: Works with `optimum-quanto` for FP8 quantization.
 
 ---