Update README.md

README.md

@@ -18,6 +18,8 @@ pipeline_tag: image-text-to-text
 library_name: transformers
 ---
 
+![1.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/EG4jDDMR4DfAJNSoMbGgg.png)
+
 # **Qwen2.5-VL-7B-Abliterated-Caption-it**
 
 > **Qwen2.5-VL-7B-Abliterated-Caption-it** is a fine-tuned version of **Qwen2.5-VL-7B-Instruct**, optimized for **Abliterated Captioning** / **Uncensored Captioning**. This model excels at generating detailed, context-rich, and high-fidelity captions across **diverse image categories** and **variational aspect ratios**, offering robust visual understanding without filtering or censorship.
@@ -104,4 +106,4 @@ This model is intended for:
 * Performance may vary on abstract or adversarial images outside of the training domain.
 * High computational demands; not optimized for edge or low-resource devices.
 * Accuracy on handwritten or heavily distorted content may be reduced.
-* As with most generative models, hallucination or context drift is possible in some scenarios.
+* As with most generative models, hallucination or context drift is possible in some scenarios.