Profile / Avatar - Nano Banana Prompt for Realistic Street Snap with Dog
by 川越あい(ラブりんって呼んでෆ)· CC-BY-4.0 license· via YouMind (CC BY 4.0)
A detailed prompt for generating a realistic street snap photo of a woman holding a toy poodle on a leash, taking a selfie. The prompt specifies camera angles, lighting, clothing details, and requires reference images for the face and…
Overview
A detailed prompt for generating a realistic street snap photo of a woman holding a toy poodle on a leash, taking a selfie. The prompt specifies camera angles, lighting, clothing details, and requires reference images for the face and outfit.
The prompt
| 1 | Face/Hair: Based on attached face photo |
| 2 | Hair state: Slightly blown by wind |
| 3 | Expression: Eyes naturally shaded by brim, gaze slightly downward towards camera, slight smile with raised corners of mouth, natural eyebrows, conveying calm emotion |
| 4 | Top: Based on attached outfit photo |
| 5 | Bottoms: Based on attached outfit photo |
| 6 | Footwear: Based on attached outfit photo |
| 7 | Clothing state: Neat, dry, normal wear |
| 8 | Accessories: Small heart-motif silver necklace, one small stud earring in one ear |
| 9 | Right hand holds black leash and brown Toy Poodle |
| 10 | Pose: Standing on both feet, right hand gripping leash, left hand extending smartphone to hold up camera. Front-facing view showing collarbone and chest. Upper body tilted slightly towards camera at approx 15 degrees, head forward of hips. Body axis tilted approx 15 degrees right from vertical. Face towards camera. Left arm bent at shoulder height in front of body (body-relative), right arm extended down at waist height beside body. Right leg straight, left knee slightly bent. |
| 11 | Depth/Foreground: Closest left hand/arm occupies approx 20% of frame, focus sharp from chest to feet, no foreground/background blur, no motion blur, moderate perspective exaggeration. |
| 12 | Composition: Full body shot (feet cut off at bottom edge), top of head approx 10% from top edge, toes approx 10% from bottom edge, person occupies approx 60% width and 90% height positioned right, high-angle camera, looking down, wide-angle lens feel. |
| 13 | Location: Outdoor paved road, daytime, spring or autumn, clear weather. Background shows edges of brown structures and grey walls occupying top 20%. Ground and shadows occupy 70%. Shallow depth of field, low bokeh. No trees/buildings visible in ground area. |
| 14 | Lighting: Main light source is direct sunlight from above, slightly high color temperature, overall high-key, medium contrast, strong distinct shadows on ground, no backlight/rim light, no visible light source in frame, no lens flare, no blown highlights. |
| 15 | Photography: Street snap type, photographer is subject (selfie) at arm's length, wide-angle focal length feel, deep aperture (pan-focus), no grain, medium saturation/contrast, crisp atmosphere. |
| 16 | Texture: Smooth skin, no sweat/wetness, deep depth of field, natural tone/white balance. |
| 17 | Style: Photorealistic (no anime/illustration/CG/painting), sharp daytime snap photo. |
| 18 | Aspect Ratio: Vertical 9:16 / 1080x1920px (no landscape) |
Similar prompts
See all →
Anime celMake Japanese TV-anime style videos (MP4) with code — cel-shaded characters with tapered line art, big detailed eyes, hair clumps with a specular band, comedic anime reactions (sweat drop, anger vein, sparkle eyes, ≥< eyes, dot eyes, tears), painted skies with cumulus clouds, school/street/classroom/rooftop sets with time-of-day palettes, speed/focus lines, impact frames, dramatic zooms, smears, sakura petals and anime subtitles (CJK). Canvas 2D rendered frame by frame in headless Chrome, encoded with ffmpeg. Use when a reference video or brief calls for anime / 動畫 / 日系動畫 / アニメ / cel-shaded / slice-of-life / school romance / shōnen-style reactions, or when the video-clone router picks the anime-cel style. 2D only; characters are original (Hina, Ren) or new ones built on the same rig.
by edenfunf · ★ 3.6k
Lemo opuscarDirect and produce a short film made entirely in code, in one of the styles of the Lemo-Opuscar library (e.g. Impasto Oil Painting 油画厚涂, Watercolor Brush 水彩笔刷, Ukiyo-e 浮世绘, Satellite Briefing 卫星简报, Exploded Teardown 产品拆解, Microscope Story 显微叙事). Use when the user asks for a video, film, short, promo, explainer or animation (视频、短片、动画、宣传片) in a named style, including data, science and product explainers built from real material such as satellite imagery, laser scans, CAD files or archive scans (数据解说、科普、产品拆解); when they want a film made about their own topic and haven't chosen a style (help them choose); or when they ask which film styles there are. Not for editing or converting existing video files.
by lemomo-ai · ★ 3.0k
Xiaohei illustrationsGenerate Ian-style Xiaohei illustrations for articles, posts, blogs, Notion documents, workflows, methods, processes, structures, states, metaphors, and opinions. Use when the user asks for weird, hand-drawn, Xiaohei, article, editorial, body illustrations, illustration ideas, shot lists, title removal, image edits, or image regeneration. By default, all image text and annotations are English, even when the source article is Chinese; only use another language when the user explicitly asks.
by dzhng · ★ 1.3k
Scenario game assetsUse when creating game art through Scenario MCP: sprites, sprite sheets, icons, props, loot, tilesets and autotile terrain transitions, seamless tiles, isometric buildings, top-down maps, pixel art, UI buttons and panels, parallax background layers or depth planes for side-scrollers, and character or concept art; or when assets need transparent backgrounds, background removal, style-consistent variation batches, upscaling, pixel-grid cleanup, or PNG export for Unity, Godot, or Unreal.
by scenario-labs · ★ 854
AI-Toolkit LoRA Trainer (WAN 2.2 & Z-Image)Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and using the result in a ComfyUI workflow.
by artokun · ★ 759
ANIMA 1.0 (Anima Base Ultra) Text-to-Image WorkflowsAnime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT). Use for anime, manga, illustrated characters; accepts Danbooru tags + natural language; runs/trains on <6GB VRAM; includes anime inpainting via Anima-LLLite ControlNetby artokun · ★ 759More from 川越あい(ラブりんって呼んでෆ)
Profile / Avatar - Autumn Cafe Frappuccino PromptDetailed prompt for an autumn-themed cafe portrait with red spider lilies and a toy poodle, suitable for Nano Banana.by 川越あい(ラブりんって呼んでෆ)
Profile / Avatar - Cafe Terrace Portrait PromptA detailed prompt for generating a photorealistic portrait of a woman in a cafe terrace setting, optimized for Nano Banana.by 川越あい(ラブりんって呼んでෆ)
Profile / Avatar - Girl Looking at Shoe on Country RoadA detailed prompt for Nano Banana Pro (gemini-3-pro-image-2k) to generate a photorealistic image of a girl looking at her shoe on a country road during sunset, based on reference photos of face and clothes.by 川越あい(ラブりんって呼んでෆ)
Profile / Avatar - Night City Dash Photo StyleA detailed prompt for generating a dynamic night city portrait, compared across models including Nano Banana Pro variants.by 川越あい(ラブりんって呼んでෆ)
Profile / Avatar - Ponytail Portrait PromptA detailed prompt for generating a realistic portrait of a young woman tying her ponytail, tested on gemini-3-pro-image-2k (nano-banana-pro).by 川越あい(ラブりんって呼んでෆ)Profile / Avatar - Realistic Indoor Portrait with Satin CamisoleA detailed prompt for generating a photorealistic portrait of a young woman in a satin camisole and pleated skirt, standing by a window. The prompt specifies lighting, pose, clothing texture, and camera settings for high-quality image generation.by 川越あい(ラブりんって呼んでෆ)Your agent, with every skill.
Connect once. Free when signed in.