k

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+from transformers import pipeline
+
+captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+
+story_gen = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-alpha", 
+                     max_new_tokens=300, do_sample=True, temperature=0.9)
+
+def image_to_story(image):
+    caption_result = captioner(image)
+    caption = caption_result[0]["generated_text"]
+
+    prompt = f"Write a short and imaginative story based on the following image description:\n\"{caption}\""
+
+    story_result = story_gen(prompt)
+    story = story_result[0]["generated_text"].replace(prompt, "").strip()
+
+    return caption, story
+
+demo = gr.Interface(
+    fn=image_to_story,
+    inputs=gr.Image(type="pil"),
+    outputs=[
+        gr.Textbox(label="Image Description (BLIP Caption)"),
+        gr.Textbox(label="Generated Story")
+    ],
+    title="🖼️→📖 Image to Story Generator",
+    description="Upload an image to generate a descriptive caption and a short creative story",
+    flagging_mode="never"
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+transformers>=4.37.0
+torch
+gradio>=4.0.0
+hf_xet