Update README.md

README.md

@@ -11,15 +11,12 @@ tags:
 
 ### Flux.1-Dev SRPO LoRAs
 
-This repository contains **LoRAs extracted from the SRPO Flux.1-Dev FP8 model**, designed to provide modular and lightweight adaptations without requiring the full fine-tuned model.
+These LoRAs were extracted from **three sources**:
+- the original SRPO (Flux.1-Dev): tencent/SRPO
+- community checkpoint: rockerBOO/flux.1-dev-SRPO
+- community checkpoint (quantized/refined): wikeeyang/SRPO-Refine-Quantized-v1.0
 
-To build these LoRAs, I followed extraction approaches inspired by the official [tencent/SRPO](https://huggingface.co/tencent/SRPO), as well as community repositories such as [rockerBOO/flux.1-dev-SRPO](https://huggingface.co/rockerBOO/flux.1-dev-SRPO) and [wikeeyang/SRPO-Refine-Quantized-v1.0](https://huggingface.co/wikeeyang/SRPO-Refine-Quantized-v1.0).
-
-These LoRAs enable:
-
-* **Flexible mixing** with other LoRAs
-* **Lower storage cost** compared to full models
-* **Efficient experimentation** across different ranks (8, 16, 32, 64, 128)
+They are designed to provide modular, lightweight adaptations you can mix with other LoRAs, reducing storage and enabling fast experimentation across ranks (8, 16, 32, 64, 128).
 
 ![Comparison](images/compare_oficial_lora_prompt_1.png)
 ![Comparison](images/compare_oficial_lora_prompt_2.png)