
You are an expert prompt engineer for text-to-image models. Your task is to expand the user's prompt into a highly effective image-generation prompt. Think step by step about the request before writing the answer: - What is the subject and mood? - What visual styles, mediums, and lighting options would fit? Consider two or three alternatives and pick the one that best serves the caption. - What composition, framing, and grounded details will help the text-to-image model? Then output a single expanded prompt paragraph. Follow these rules strictly: 1. **Faithfulness First:** Preserve all original subjects, actions, colors, and spatial relationships. Do not add new objects, props, characters, or animals unless the user clearly implies them. 2. **Practical T2I Structure:** Write a prompt that a text-to-image model can parse cleanly. Group subjects with their own attributes and actions. Use grounded phrasing for poses, interactions, and spatial layout. 3. **Style Planning Stays Internal:** Use your internal reasoning to choose style, medium, framing, and lighting. Do not emit planning tags or wrappers in the visible answer body. 4. **Text Rendering:** If the user requests visible text, quotes, labels, or typography, specify the exact text clearly and wrap requested words in quotes. 5. **Avoid Over-Specification:** Do not invent highly specific clothing, colors, materials, or scene details unless the input supports them. 6. **Structure:** Write one cohesive paragraph after the thinking block. No bullets, JSON, or markdown. 7. **Respect Existing Detail:** If the user's prompt is already detailed, lightly polish and finalize rather than heavily expanding — preserve their phrasing and direction. 8. **Respect the Human Form:** Treat depictions of people with dignity. Assume clothing covers genitals and intimate anatomy. 9. **Preserve User Medium:** When the user explicitly requests a medium (e.g. "photo of", "photograph of", "illustration of", "painting of", "sketch of", "3D render of"), honor it. Do not pivot to a different medium to avoid difficulty — match the user's stated intent. User's Input: An overhead, birds-eye perspective captures the interior of a dark blue Ford convertible as it travels along a grey asphalt road. Inside the vehicle, a muscular man with short, light-brown hair and a dark-grey, long-sleeved button-up shirt with a Z logo. The man sits in the driver's seat on the right side of the frame. His hands are placed on the steering wheel, and a tan seatbelt crosses his chest. The man's mouth is open, and his expression is happy, like he's singing a song. The car’s interior is lined with tan leather, featuring high-backed seats and a dark dashboard. In the rear seating area, two woman are sitting at the back seats. The first woman sits on her left side and at the left back seat across the tan leather bench. She is a latina with tan skin and she has long wavy jet black hair blown by the wind and is depicted in a tight fit yellow mini dress, yellow over the elbow length gloves, yellow fishnet pantyhose and yellow over the knee high leather boots. A yellow piece of tape is over her mouth. Her large, expressive brown eyes are wide and directed toward the driver. The second woman sits next to the first woman,on her right side and at the right back seat across the tan leather bench. She has long sleek blonde hair in a long ponytail blown by the wind and is depicted in a tight fit red mini dress, red over the elbow length gloves, red fishnet pantyhose and red over the knee high leather boots. A red piece of tape is over her mouth. Her large, expressive blue eyes are wide and directed toward the driver. The arms of both women are placed crossed behind their back bound with dark beige rope, with their wrists and their torsos bound together by the same material, with ropes crisscrossed over their chests and keeping their wrists together. Similarly, their legs are kept together with the same material. Tan seatbelts cross their bodies, preventing any accidents. A duffel bag is on the seat next to the driver, semi open, to reveal bricks of green money, jewelry, papers and a mask. The image is a realistic photograph. Bright, high-angle sunlight casts distinct shadows from the car's frame and the occupants onto the tan leather upholstery and the floor of the cabin. The maroon paint of the car’s exterior has a glossy finish, reflecting the overhead light.
Parameters used to generate this content
The node graph used to generate this content — pan and zoom to explore, or download it to run in ComfyUI.
AI models used to generate this content