Enable Gemma4 video input

site/docs/use-cases/image-processing/_sections/_usage_options/index.mdx

@@ -26,13 +26,15 @@ The prompt can contain `<ov_genai_image_i>` with `i` replaced with an actual zer
 12. Qwen2.5-VL: `<|vision_start|><|image_pad|><|vision_end|>`
 13. Qwen3-VL: `<|vision_start|><|image_pad|><|vision_end|>`
 14. gemma-3-4b-it: `<start_of_image>`
+15. gemma4: `<|image|>`
 
 Model's native video tag can be used to refer to a video. These tags are:
 1. LLaVA-NeXT-Video: `<video>`
 2. Qwen2-VL: `<|vision_start|><|video_pad|><|vision_end|>`
 3. Qwen2.5-VL: `<|vision_start|><|video_pad|><|vision_end|>`
 4. Qwen3-VL: `<|vision_start|><|video_pad|><|vision_end|>`
 5. VideoChat_Flash_Qwen: `<|image_i|>\n` - the index starts with one
+6. gemma4: `<|video|>`
 
 If the prompt doesn't contain image or video tags, but images or videos are provided, the tags are prepended to the prompt.