Update README.md

README.md

@@ -27,23 +27,9 @@ The **FLUX.1 [dev] Abliterated** model is a modified version of the original FLU
 
 The abliteration process involves identifying and isolating the specific components of the model responsible for refusal behavior and then modifying or ablating those components. This results in a model that is more flexible and responsive, while still maintaining the core capabilities of the original FLUX.1 [dev] model.
 
-#### Key Features
-- **Cutting-Edge Output Quality:** Retains the high-quality image generation capabilities of FLUX.1 [dev], producing visually stunning and detailed images.
-- **Enhanced Flexibility:** The abliteration process allows the model to respond to a broader range of prompts, including those that might have been restricted in the original model.
-- **Open Weights:** The model is open-source, enabling researchers, developers, and artists to explore and build upon its capabilities.
-- **Efficient Inference:** Despite the modifications, the model remains efficient and can be run on consumer-grade GPUs.
-- **Commercial Use:** Generated outputs can be used for personal, scientific, and commercial purposes, as described in the FLUX.1 [dev] Non-Commercial License.
-
-#### Intended Use
-The FLUX.1 [dev] Abliterated model is intended for use in:
-- **Creative Applications:** Artists and designers can use the model to generate unique and imaginative visuals based on text prompts.
-- **Research:** Researchers can explore the effects of abliteration on model behavior and study the mechanisms behind refusal in large language models.
-- **Commercial Projects:** The model can be used in commercial applications, such as advertising, content creation, and more.
-
-#### Limitations
-- **Ethical Considerations:** The removal of the refusal mechanism means that the model may generate content that could be considered inappropriate or harmful. Users should exercise caution and implement additional safeguards when deploying this model.
-- **Quality Degradation:** In some cases, the abliteration process may lead to a slight degradation in output quality or coherence. Fine-tuning or additional post-processing may be required to mitigate this.
-- **Bias and Fairness:** Like all large language models, FLUX.1 [dev] Abliterated may exhibit biases present in the training data. Users should be aware of these biases and take steps to address them in their applications.
+#### Architecture
+
+![Architecture](flux.jpg)
 
 #### Usage
 To use the FLUX.1 [dev] Abliterated model, you can load it via Hugging Face and generate images using the following code: