Genur.art

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: A terrified but beautiful 25-year-old Latina woman with her arms bound behind her back and her wrists and elbows tied, trying to run through a dense forest at night, her expression wide-eyed and panicked, sweat glistening on her face as she glances behind her. Her arms are bound behind her back with jute ropes. She wears a torn charcoal mini pencil skirt with a slit that has grown larger from tearing, and that is full of mud and tearings. Above that, she wears a tight red torn shortsleeved blouse with a turtleneck, the fabric damp with dew and torn by branches. Her black hair is long messy and disheveled, strands sticking to her face as she sprints across uneven terrain. Her mouth is gagged by a dirty old piece of grey fabric and her arms are bound with ropes behind her back. Her wrists are held together behind her back with ropes, restricting her movement. Her movement makes her large firm breasts pop up. Her legs are bruised from the branches and her fishnet pantyhose are ripped and torn and her dirty black knee high lace-up boots with stiletto heels are in a bad condition from the mud and the broken heels. The moonlight pierces through the thick canopy, casting stark shadows on the mossy ground, illuminating the trees in a cold blue hue. The forest is alive with eerie stillness, fog swirling around the underbrush, faint beams of light catching her figure in motion. A dark male figure is seen at the back, chasing her. Camera angle is low and dynamic, capturing her in mid-stride from a side perspective, emphasizing motion blur and urgency. Leaves and twigs scatter under her feet as she dashes past gnarled trees and roots. The atmosphere is tense and cinematic, evoking suspense and danger lurking in the unseen dark.