Concise 2-sentence description (model first, then inputs)

app.py

@@ -179,10 +179,9 @@ def generate(subject, scene, soundscape, music, raw_prompt, img1, img2, img3,
 HEADER = """
 <div class="fh-header">
   <h1>FastH3 · <span class="fh-accent">OmniRef</span> reference-to-video</h1>
-  <p>Give it one or more <b>reference images</b> (and, optionally, a <b>reference audio</b> clip), then
-  describe the <b>subject</b> and the <b>scene</b>. The FastVideo FastH3 OmniRef student generates a short
-  <b>video with a matching soundtrack</b> in eight fused forwards, keeping your reference subject. Your
-  words are assembled into the model's six-section H3 prompt format automatically.</p>
+  <p>FastH3 OmniRef is FastVideo's 8-step reference-to-video student that turns reference images plus a
+  prompt into a short clip with a matching soundtrack. Add one or more reference images (and optional audio),
+  describe the subject and scene, and the prompt is assembled into the model's six-section H3 format for you.</p>
   <div class="fh-pills">
     <a href="https://huggingface.co/FastVideo/FastH3-OmniRef-NVFP4-QAD" target="_blank">FastH3 OmniRef</a>
     <a href="https://github.com/hao-ai-lab/FastVideo" target="_blank">FastVideo</a>