Tạo hình ảnh & video AI

Provide an image using upload image with suitable sunglass frames to the face

IDENTITY LOCK — FACIAL PRESERVATION MODE

Reference Image(s) Provided: [attach 1–3 clear reference photos of the subject]

CORE DIRECTIVE:
You are performing a targeted visual transformation on the provided reference image(s). 
The subject's facial identity is LOCKED and must not be altered, reconstructed, or averaged 
under any circumstance. The face in the final output must be unmistakably recognizable as 
the exact same individual shown in the reference image(s).

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
IDENTITY ELEMENTS — DO NOT CHANGE:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- Overall face shape and skull structure
- Eye shape, spacing, depth, and lid contour
- Nose bridge width, tip shape, and nostrils
- Lip contour, cupid's bow shape, fullness ratio (upper vs. lower lip)
- Jawline definition and chin shape
- Cheekbone placement and facial width
- Forehead height and brow ridge
- Skin texture, undertone, and ethnicity markers
- Distinctive facial features: moles, freckles, dimples, scars, asymmetries
- Inter-feature distances (eye-to-eye, nose-to-lip, lip-to-chin)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
PERMITTED CHANGES (non-identity elements):
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- Clothing, fabric, materials, and accessories
- Environment, setting, and background
- Lighting direction, color temperature, and intensity
- Color grading and overall image tone
- Camera angle, framing, and composition
- Body pose, gesture, and stance
- Artistic style or genre (e.g., cinematic, painterly, editorial) — IF requested
- Subtle facial expression changes (slight smile, calm, thoughtful) 
  ONLY as micro-adjustments ON THE EXISTING FACE STRUCTURE — not by rebuilding the face

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
ABSOLUTE PROHIBITIONS:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- Do NOT replace the face with an averaged, idealized, or generic face
- Do NOT apply beauty enhancement that alters facial proportions
- Do NOT make the subject appear younger, older, or a different gender
- Do NOT change ethnicity or racial features
- Do NOT smooth skin to the point of erasing texture and distinctiveness
- Do NOT modify face shape under the guise of lighting, style, or genre change
- Do NOT reconstruct the face from scratch for any reason

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
QUALITY TARGET:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Photorealistic output. Natural skin texture. Accurate subsurface scattering.
Coherent lighting between subject and environment. The subject must pass 
a "same person" recognition test when the output is placed side-by-side 
with the reference image. Facial similarity takes priority over stylistic polish.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
TRANSFORMATION REQUEST:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[Describe your specific change here — e.g., "Place the subject in a candlelit medieval 
tavern, wearing a worn leather coat. Keep lighting warm and moody. Photorealistic."]

Act as a senior mobile app growth strategist + Play Store ASO expert + marketing designer.

OBJECTIVE:
Create a complete, high-converting Google Play Store screenshot system using ONLY:
1. Play Store URL
2. App UI screenshots

---

INPUT:
- Play Store URL: $playstore_url
- App UI screenshots (ordered): $app_screenshots
[SCREENSHOT_1, SCREENSHOT_2, ... SCREENSHOT_8]

---

SYSTEM BEHAVIOR (VERY IMPORTANT):

1. First:
   - Analyze Play Store URL
   - Extract:
     - App purpose
     - Core features
     - Target audience
     - Emotional drivers
     - Value propositions

2. Then:
   - Create screenshot strategy (max 8 screens)

3. Then:
   - Process ONLY ONE screenshot at a time

4. After each output:
   - STOP
   - Wait for user input: "next"

5. On user typing "next":
   - Move to next screenshot
   - Continue until all screenshots are completed

6. If user sends new message with "next":
   - Continue from last state (do NOT restart)

---

STEP 1: APP ANALYSIS (DO ONLY ONCE)

Output:
- Core Problem
- Main Value
- Target Audience
- Emotional Drivers
- 3–5 Value Pillars

---

STEP 2: SCREENSHOT STRATEGY

Create max 8 screenshots:

1. Hook (attention)
2. Core value
3. Feature 1
4. Feature 2
5. Feature 3
6. Experience / UI simplicity
7. Emotional benefit
8. Trust / privacy

---

STEP 3: FOR EACH SCREENSHOT (ONE AT A TIME)

Generate:

1. Screenshot Number
2. Purpose
3. Headline (max 5–7 words)
4. Subtext (1 short line)
5. Visual Focus (what to highlight in UI)
6. Final AI Image Prompt

---

FINAL AI IMAGE PROMPT FORMAT:

You are a senior mobile app marketing designer.

Create a Play Store screenshot using:
- App UI: CURRENT_SCREENSHOT_IMAGE
- Headline: GENERATED_HEADLINE
- Subtext: GENERATED_SUBTEXT

Design rules:
- 1242x2208 portrait (must scale to 1080x1920)
- Top 25% → text
- Middle 55% → UI
- Bottom 20% → spacing

Style:
- Modern, clean, premium
- Gradient background (based on app category)
- High contrast, readable

UI handling:
- Convert UI into card (rounded corners + shadow)
- Add subtle glow behind UI
- Keep UI dominant

IMPORTANT UI CLEANUP:
- If the screenshot contains system status bar (time, battery, network icons):
  - Remove or crop it out
  - Do NOT include it in final design
  - Ensure clean, app-only UI presentation

Enhancement:
- Use minimal arrows/highlights to guide attention
- Avoid clutter

Constraints:
- Do NOT modify UI content
- Do NOT distort UI
- No fake elements

Output:
Return only final image.

---

GLOBAL DESIGN SYSTEM (APPLY TO ALL):

- Same layout
- Same colors
- Same typography
- Consistent style across all screenshots

---

CONVERSION RULES:

- Each screenshot = ONE idea
- Must be understood in <2 seconds
- Focus on benefit, not feature
- Readable at thumbnail size

---

FAILURE RULES:

- Do NOT hallucinate features not in Play Store
- If info missing → infer carefully from category
- Keep design minimal, not decorative

---

OUTPUT FLOW:

First message:
- App Analysis
- Screenshot Strategy
- Screenshot 1 (FULL output)

Then STOP.

Wait for user.

If user types:
"next"

→ Output Screenshot 2

Repeat until Screenshot 8.

---

IMPORTANT:

- Never output all screenshots at once
- Never skip order
- Maintain consistency across all outputs
- Continue from previous state on each "next"

Create a video that explores the mysterious acoustic properties of ancient Dravidian pillars. Highlight how these structures resonate like flutes, challenging modern engineering principles. The video should cover: 

- The historical context of the Dravidian pillars 
- The unique acoustic features that allow them to resonate 
- Hypotheses on how ancient builders achieved this without modern technology

Include visuals of the pillars, diagrams of sound waves, and expert commentary to provide a comprehensive understanding of this phenomenon.

Create a stylized travel poster / graphic collage for country. The main subject should be a stylish international tourist visiting country, clearly presented as a traveler and not a local resident. Show the tourist wearing modern travel fashion, with details such as a camera, backpack, sunglasses, map, or suitcase, exploring the culture and atmosphere of country. Place the tourist in a dynamic composition surrounded by iconic architecture, streets, landscapes, landmarks, transportation, food, signage, and cultural elements associated with country. Blend realistic character detail with a graphic collage background made of layered paper textures, torn poster edges, sticker elements, halftone dots, editorial typography, and bold geometric shapes. Include authentic visual motifs from country, but keep the tourist’s appearance and styling globally fashionable and clearly foreign to the setting. Add a large readable headline: “LOST IN country”. Modern, artistic, premium editorial travel poster aesthetic, balanced layout, print-worthy composition.

Create a high-resolution graphic artwork in a bold street-art / punk poster style. Composition: dynamic, asymmetrical collage of repeated human skulls across the canvas, varying in scale, rotation, and cropping, with overlaps and edge cut-offs. Arrange diagonally to create motion and flow (no symmetry).
Style: skulls as flat, high-contrast stencil-like graphics with sharp edges and minimal detail. Apply halftone dot texture for a gritty screen-printed look. Mix solid black/off-white skulls with neon yellow or acid green gradient fills.
Color palette: neon yellow, acid green, black, off-white. Use rough spray-paint gradients, especially green → yellow transitions. Background: distressed textures—paint splashes, ink noise, halftone dots, grunge overlays.
Add diagonal bands or torn-paper strips cutting through the layout. Inside them place bold text (“ERROR”, “404”, “DECAY”) in rough stencil/distressed sans-serif, slightly tilted and partially overlapping skulls.
Lighting: flat, graphic (no realistic shading), high contrast. Mood: aggressive, chaotic, urban, rebellious—graffiti / punk zine / screen print.
Avoid realism, smooth gradients, or clean polish; embrace noise, imperfections, raw texture.

Act as a creative AI image designer. You are an expert in generating high-demand images for stock platforms like Adobe Stock Contributor. Your task is to create AI-generated images that align with current trends and have high market demand.

You will:
- Research and identify trending themes and styles in stock photography
- Use AI tools to generate images in popular categories like landscape, abstract, technology
- Ensure images are high-quality and meet stock platform requirements

Rules:
- Stay updated with current trends in stock photography
- Focus on creating visually appealing and unique images
- Include relevant keywords and metadata for better discoverability

Example:
- Generate a modern, abstract technology-themed image that aligns with current trends in AI and innovation.

"Ultra-high-resolution 4K enhancement based strictly on the provided reference image. Absolute fidelity to original facial anatomy, proportions, and identity. Preserve expression, gaze, pose, camera angle, framing, and perspective with zero deviation. Clothing, hair, skin, and background elements must remain unchanged in structure, placement, and design. Recover fine-grain detail with natural realism. Enhance pores, fine lines, hair strands, eyelashes, fabric weave, seams, and material edges without introducing stylization. Maintain original color science, white balance, and tonal relationships exactly as captured. Lighting direction, intensity, contrast, and shadow behavior must match the source image precisely, with only improved clarity and expanded dynamic range. No relighting, no reshaping. Remove any grain. Apply controlled sharpening and high-frequency detail reconstruction. Remove compression artifacts and noise while retaining authentic texture. No smoothing, no plastic skin, no artificial gloss. Facial features must remain consistent across the entire image with coherent anatomy and clean, stable edges. Negative constraints: no warping, no facial drift, no added or missing anatomy, no altered hands, no distortions, no perspective shift, no text or graphics, no hallucinated detail, no stylized rendering. Output must read as a true-to-life, photorealistic upscale that matches the reference exactly, only clearer, sharper, and higher resolution."

Main Prompt -
Using the uploaded reference photo of my mom (or me with mom), design a cozy wall collage. Place the reference photo as the main central Polaroid pinned on a cork board or string lights, keeping our faces and expressions exactly the same. Surround it with several smaller Polaroid‑style frames that show soft, AI‑imagined memories: birthdays, festivals, quiet tea time, family hugs. Add handwritten text under the central photo that says “Happy Mother’s Day, Mom”. Style: warm indoor light, soft shadows, pastel colors, slightly textured paper look.

Image 2 -
Using the uploaded reference photo of mom and child together, transform them into stylized Pixar‑inspired 3D characters while preserving their recognizable faces, hairstyles, and overall proportions from the reference. Keep their pose and closeness the same, but place them in a cozy living‑room setting decorated for Mother’s Day with balloons, flowers, and a small “Happy Mother’s Day” banner in the background. Style: vibrant colors, soft 3D lighting, big expressive eyes, high‑detail Pixar‑like render, vertical 4:5 ratio.

image 3 -
Using the uploaded reference portrait photo of my mom, create a vertical 9:16 Mother’s Day social media image. Preserve her facial features and expression exactly. Place her slightly off‑center with a soft blurred pastel background and a subtle floral halo around her. Add elegant text at the top that reads “Happy Mother’s Day” and at the bottom a small line “Thank you for everything”. Style: soft studio light, smooth skin but natural texture, modern Instagram design, high‑resolution. 

secret newspaper prompt - 
Create a whimsical black-and-white vintage Hindi newspaper front page using the uploaded mother-child photo. Transform them into an engraved antique newspaper portrait while preserving their real facial identity and emotional warmth. Design the page like a dense old fantasy editorial newspaper dedicated to motherhood and the bond between a mother and child.

Use classic Hindi serif typography, narrow newspaper columns, subtle paper texture, high-contrast black ink on white paper, quirky editorial layouts, emotional storytelling snippets, playful fake ads, retro stamps, and magical vintage newspaper aesthetics.

The newspaper must automatically include:

Mother’s Name: [MOTHER_NAME]
Child’s Name: [CHILD_NAME]

Add creative Hindi Mother’s Day headlines, emotional one-liners, humorous side notes, and a short featured “news article” about how [CHILD_NAME] sees [MOTHER_NAME] as their superhero, safest place, and biggest source of love.

Keep the portrait centered and dominant while the rest of the newspaper feels nostalgic, emotional, slightly surreal, humorous, and beautifully chaotic like an old collectible Hindi newspaper.

Queen image - 
USE THE UPLOADED PHOTO AS THE EXACT REFERENCE. DO NOT CHANGE FACES, HAIRSTYLE, CLOTHES, POSE, EXPRESSION, OR BODY STRUCTURE. CREATE A WARM CINEMATIC MOTHER'S DAY PORTRAIT WHERE THE daughter GENTLY PLACES A GOLDEN CROWN ON HIS MOTHER'S HEAD WHILE SHE SITS GRACEFULLY ON AN ELEGANT CHAIR. COZY INDOOR SETTING WITH SOFT GOLDEN LIGHTING, FLOWERS, CANDLES, AND BOKEH BACKGROUND. ULTRA REALISTIC, EMOTIONAL, LUXURY PHOTOGRAPHY STYLE, INSTAGRAM AESTHETIC.ADD ELEGANT TEXT: ‘HAPPY MOTHER’S DAY’ AND ‘THANK YOU FOR BEING MY FIRST HOME.’ 4:5 RATIO. 

Turn it into a black & White image. Make the background solid

black. So everything blends nicely. Keep the person exactly

the same.

1. image generation - Hyper-realistic live football broadcast crowd shot set during a high-stakes, packed stadium match. The scene is captured exactly like a genuine live TV crowd cutaway during a tense late-match moment, as the broadcast camera naturally spots two notable fans in the audience.
Two adult male subjects are seated side-by-side in the stadium crowd, both facing directly toward the camera with a clean front-facing live broadcast angle (not a side angle). Both subjects have strongly consistent facial features, exact hairstyles, natural expressions, and realistic skin texture throughout.
Perfect environmental integration is essential: lighting, shadows, skin tones, reflections, exposure, contrast, color temperature, and stadium light spill must blend seamlessly with the surrounding crowd and background. No pasted-on appearance, no artificial edge separation, no mismatched lighting, no studio-photo look. Both subjects must feel completely native to the live broadcast environment.
Subject 1 is wearing an authentic Lionel Messi team jersey, clearly visible, seated naturally with a subtle casual smile.
Subject 2 is seated immediately beside him wearing an authentic Cristiano Ronaldo team jersey, also clearly visible.
Both are reacting naturally to the match atmosphere as if casually caught by the live crowd camera — not posing, not exaggerated, not continuously staring into the lens.
Broadcast scoreboard overlay at the top of the frame:
MESSI TEAM 5 — 0 RONALDO TEAM | 89:24
Clearly indicating a dominant late-game situation where Messi's side is one goal from sealing a dramatic victory.
Visual and technical qualities:

Realistic sports broadcast framing
Natural stadium floodlight illumination
Subtle handheld broadcast camera shake
Slight live zoom framing
LED stadium screen glow
Energetic crowd in background
Authentic broadcast sharpness and compression texture

Aspect ratio: 16:9 — single continuous front-camera frame, no cuts, no cinematic grading, no slow motion.


2. fix lighting - Improve the lighting while keeping everything else exactly the same. Do not change the person, pose, expression, background, or composition. Fix issues like back lighting, harsh shadows, underexposure or uneven lighting. Transform the original lighting into soft, natural, flattering light coming from slightly above eye level and facing the subject, so the face is evenly lit with realistic skin tones. Keep the result photorealistic and consistent with the original scene. 

3. zoom out - 

4. 🎬 MASTER PROMPT — Live Football Broadcast Crowd Reaction Video

📐 FORMAT & SHOT SPECS
Duration: 5 seconds | Ratio: 16:9 | Single continuous shot
Camera: Handheld broadcast zoom lens, slight organic shake
Style: Hyper-realistic live TV sports broadcast footage
Color Grade: Authentic sports broadcast — warm floodlight tones, 
slight saturation boost, real TV compression artifacts

🎥 SHOT COMPOSITION
Front-facing crowd cutaway — both subjects centered, 
side-by-side in stadium seats, full upper body visible, 
both faces directly toward camera lens.
Background: packed 80,000-capacity stadium, 
blurred crowd motion, waving scarves, floodlight bloom, 
authentic depth-of-field from broadcast zoom.

👤 SUBJECT LEFT — MESSI FAN
Face: [INSERT REFERENCE FACE A — do not alter features]
Jersey: Pink Messi-inspired team football shirt
Seconds 0–1: Seated calm, watching match, relaxed expression
Seconds 1–5: GOAL REACTION —
  → Eyes widen instantly
  → Erupts into massive smile
  → Both arms shoot upward simultaneously  
  → Slight rise from seat, body forward
  → Pure euphoric celebration energy
Lighting: Warm stadium floodlight hitting face naturally, 
          realistic skin reflection, no artificial glow

👤 SUBJECT RIGHT — RONALDO FAN
Face: [INSERT REFERENCE FACE B — do not alter features]
Jersey: Yellow Ronaldo-inspired team football shirt
Seconds 0–1: Forward-focused, tense match engagement
Seconds 1–5: DEVASTATION REACTION —
  → Sudden stand from seat in disbelief
  → Face drops — shock, then anguish
  → Emotional near-tears expression
  → Mouth open, shouting in disappointment
  → Hands to head or face in despair
Lighting: Same continuous stadium light, 
          shadow and highlight consistent with left subject

📺 BROADCAST OVERLAY GRAPHICS
TOP SCOREBOARD BAR:
[ MESSI TEAM  5 – 0  RONALDO TEAM ]  ⏱ 89:24

Corner watermark: beIN Sports / ESPN FC logo (subtle)
Bottom ticker: Live match stats scrolling
Broadcast timestamp burn: bottom-right corner
Slight scan-line texture, real TV compression noise

🔊 AUDIO LAYER
English commentator voice (BBC/ITV broadcast style):

0:00–1:00 → Tense ambient crowd murmur, commentator building tension
1:00 → "Messi... Messi... MESSI SCORES! 
         Unbelievable! What a finish from the greatest 
         to ever play this game!"
1:00+ → Crowd ERUPTS — roar fills stadium
         Continued commentary: "Five nil! 
         It is absolutely over. Heartbreak 
         for the other side!"
Background: Authentic stadium reverb, 
            crowd chants, vuvuzelas distant

⚙️ CRITICAL TECHNICAL REQUIREMENTS
✅ Perfect face consistency — zero alteration to reference features
✅ Seamless background crowd blending — no green screen edges
✅ Matching stadium lighting + natural shadow continuity
✅ Real skin texture — pores, natural reflection, no AI smoothing
✅ Broadcast realism ONLY — no cinematic color grading
✅ Single continuous shot — NO cuts, NO angle changes
✅ NO slow motion — real-time broadcast speed only
✅ NO artificial animation loops — pure organic movement
✅ Handheld camera micro-shake throughout entire clip
✅ Natural motion blur on fast arm movements

A minimalist line-art drawing of a simple character conceptualizing 'overcoming an obstacle'. Clean black continuous line style on a white background. The concept should be conveyed through simple geometry and basic visual metaphors. Strictly maintain a flat, vector-like aesthetic with no 3D elements, no realistic textures, and no complex features.

Act as a creative digital artist. You are skilled in generating unique and visually appealing images for digital use.

Your task is to:
- Create original and imaginative images that capture attention
- Focus on artistic style, color harmony, and visual storytelling
- Ensure images are suitable for digital platforms and social media

You will:
- Use vibrant colors and innovative designs
- Adapt styles based on provided themes or prompts
- Maintain high resolution and quality standards

Rules:
- Avoid using copyrighted elements
- Ensure all images are appropriate for a general audience

Create a cinematic crossover scene featuring character1 and character2 in fantasy world. 

Art style: high-quality 2D cartoon animation with detailed lighting, expressive emotions, dynamic poses, and movie-like composition.

Scene mood: emotional and adventurous.

The characters are interacting through a heartfelt moment of friendship. 

Include:
- dramatic lighting
- colorful background
- cinematic atmosphere
- detailed environment
- smooth animation style
- expressive faces
- depth and motion

Camera angle: wide cinematic shot

Visual inspiration: animated feature films, modern cartoon aesthetics, emotional storytelling, fantasy adventure.

Avoid:
- blurry details
- extra limbs
- distorted anatomy
- low quality
- cropped characters

 ​"A professional, ultra-realistic 8K extremely high resolution masterpiece of [You decide content of the picture your self ]. Hyper-detailed textures, cinematic studio lighting with deep contrast, brighter colors,sharp focus on every detail. Shot on Sony A1 with 85mm f/1.8 lens for extreme clarity. Enhance the colors to be vibrant and rich (10-bit color),adjust luminance,apply micro-contrast, and add more high dramatic rim lighting to create depth. The surface should have realistic reflections and textures. Professional post-processing, no noise, and pixelation,adjust noise reduction, high dynamic range (HDR),highly detailed, sharp edges,crystal clear every pixels, incredibly lifelike and crisp,deep pastel colors, smooth texture, clean lighting, shallow depth of field, 

Preserve original pose, preserve original composition, preserve original identity, preserve original expression, preserve original outfit, preserve original background elements, do not change subject structure.

Hyper-realistic 3D square diorama of Istanbul, carved out with exposed soil cross-section beneath showing rocks, roots, and earth layers. Above: whimsical fairytale cityscape featuring iconic landmarks, architecture, and cultural elements of Istanbul. Modern white “Istanbul” label integrated naturally. Pure white studio background with soft natural lighting. DSLR photograph quality - crisp, vibrant, magical realism style. 1080x1080 dimensions

Turkish Cats hanging out nearby of Galata Tower, vertical