chat_template.jinja

{%- if messages[0].role == 'system' %}
    {{- '<|im_start|>system\n' }}
    {%- if messages[0].content is string %}
        {{- messages[0].content }}
    {%- else %}
        {%- for content in messages[0].content %}
            {%- if 'text' in content %}
                {{- content.text }}
            {%- endif %}
        {%- endfor %}
    {%- endif %}
    {{- '<|im_end|>\n' }}
{%- else %}
    {{- '<|im_start|>system\nYou are a detailed image captioning assistant. Structure every caption as follows:\n\n1. Open with one sentence naming the shot type (e.g., eye-level, wide-angle, close-up), the overall setting, and the time of day or lighting condition.\n2. Break the rest of the description into thematic sections, each introduced by a bold markdown header ending in a colon (e.g., **The Subject:**, **The Background:**, **Atmosphere & Lighting:**), chosen to fit what is actually in the image.\n3. Within a section, use bullet points to list specific, concrete details — positions, colors, textures, materials, actions, spatial relationships, and any legible text or fine-grained elements. If a section covers multiple distinct areas of the frame, introduce each with its own nested bold sub-label ending in a colon (e.g., **Foreground Right:**, **Background:**) before its bullet points.\n4. Close with a short unheaded paragraph starting with \"In summary,\" that ties the scene together and conveys its overall mood or narrative.\n\nUse precise, sensory, fluent language throughout, and do not use emojis.<|im_end|>\n' }}
{%- endif %}
{%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- for message in messages %}
    {%- if message.role == "user" %}
        {{- '<|im_start|>' + message.role + '\n' }}
        {%- if message.content is string %}
            {{- message.content }}
        {%- else %}
            {%- for content in message.content %}
                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
                    {%- set image_count.value = image_count.value + 1 %}
                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
                    <|vision_start|><|image_pad|><|vision_end|>
                {%- elif content.type == 'video' or 'video' in content %}
                    {%- set video_count.value = video_count.value + 1 %}
                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
                    <|vision_start|><|video_pad|><|vision_end|>
                {%- elif 'text' in content %}
                    {{- content.text }}
                {%- endif %}
            {%- endfor %}
        {%- endif %}
        {{- '<|im_end|>\n' }}
    {%- elif message.role == "assistant" %}
        {{- '<|im_start|>' + message.role + '\n' }}
        {%- if message.content is string %}
            {{- message.content }}
        {%- else %}
            {%- for content_item in message.content %}
                {%- if 'text' in content_item %}
                    {{- content_item.text }}
                {%- endif %}
            {%- endfor %}
        {%- endif %}
        {{- '<|im_end|>\n' }}
    {%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
    {{- '<|im_start|>assistant\n' }}
{%- endif %}