پرامپت | My Prompt
772K subscribers
2.44K photos
124 videos
1 file
612 links
Official Channel of the DiGiAi AI Platform.

ارتباط : @DigiAiSup

ساخت عکس : @PhotoAi_robot
Download Telegram
پرامپت تولدی

img1 exact face, hair and appearance, 100% likeness, no changes. Ultra-realistic iPhone 15 Pro Max Night Mode birthday portrait, natural candid smartphone photo, not studio-style. Woman in a 3/4 pose, head turned slightly toward her shoulder, direct eye contact with a soft closed-mouth smile, holding a round birthday cake with both hands at chest level. Preserve img1 hair exactly. Black silky satin strapless/off-shoulder dress with draped sleeves, delicate tennis necklace and bracelet, glossy classic red nails. Cream cake with glossy burgundy-strawberry topping and one tall sparkling silver candle. Dark rooftop/terrace at night, deep navy sky, blurred city bokeh, soft square ambient light, subtle concrete edge in foreground. Warm candlelight on hands and cake with gentle facial fill, natural Night Mode texture and intimate party atmosphere.


@Digiai
پرامپت عکس دانشجویی:

portrait of a young woman with hair parted down the middle with loose , naturally defined brows, soft glowing without makeup natural face, pink shade lips color , looking to the camera with gentle smile. She wears a smooth black "Iranian school girls headscarf مقنعه " neatly draped, matching black garment with a single round muted purple button on the sleeve. Resting her cheek gently on her hand, soft relaxed expression. Background: sunny day with clouds in the sky , photorealistic, sharp focus on face, natural skin texture, warm soft color grading, elegant modest aesthetic, high detail, 8K


@Digiai
🧬 کشف بزرگ آنتروپیک در ژنتیک: Claude آنزیم جدیدی شبیه به کریسپر در DNA شناسایی کرد!

هوش مصنوعی Claude با بررسی حجم خیلی زیادی از اطلاعات DNA، به یک سیستم آنزیمی جدید رسیده که شباهت‌هایی به «کریسپر» داره؛ همون فناوری معروفی که برای کار روی DNA و ویرایش ژن‌ها استفاده میشه.

برای این کار حدود ۹۵۰ ایجنت هوش مصنوعی، نزدیک ۲۱ ساعت روی اطلاعات بیش از ۲۰۰ هزار آنزیم کار کردن و بیشتر از ۲۱۰ میلیون توکن مصرف شد.

نتیجه این بررسی‌ها پیدا شدن سیستمی به اسم ART بود؛ سیستمی که می‌تونه راه‌های تازه‌ای برای کار با DNA و ابزارهای ژنتیکی باز کنه.


@Digiai
به عکسات یه افکت خاص بده:

Add an authentic early-2000s digital camera look: cool blue tint, harsh direct flash, crushed blacks, blown highlights, low resolution, visible pixelation, digital noise, slight motion blur, chromatic fringing and subtle VHS-like scanlines. Keep the original person, outfit and composition unchanged.


@Digiai
پرامپت بارداری:

Use the uploaded photo as the ONLY identity reference. Preserve the subject’s exact recognizable facial features, natural proportions, skin tone, hair, apparent age, and overall identity. Do not beautify, reshape, feminize, masculinize, or change the face.

This prompt must work for any adult subject, male or female. Regardless of gender, portray the same person as realistically 8 months pregnant, with a naturally rounded late-pregnancy belly integrated anatomically into their existing body proportions.

Create an ultra-photorealistic luxury fashion maternity portrait. The subject stands in a graceful three-quarter pose, looking down at their belly with a calm expression, one hip slightly raised, both hands naturally supporting the belly from underneath.

Dress them in an elegant fitted white satin maternity outfit with a refined open-back design, adapted naturally to the subject while preserving their original identity and gender presentation.

Studio setting with a neutral light background. Project large pink forget-me-not branches as LIGHT ONLY across the wall, skin, hands, belly, and clothing. The floral pattern must clearly look like projection mapping, naturally wrapping and fading across surfaces. No real flowers, bouquets, petals, or physical floral props.

Warm soft studio lighting, subtle rim light, luxury fashion editorial aesthetic, knee-up vertical portrait, 85mm lens, shallow depth of field, realistic skin and fabric texture, cinematic, ultra-detailed, no text, no watermark.


@Digiai
گوگل فوتوز یه «کمد مجازی» آورده که با هوش مصنوعی لباس‌ها و اکسسوری‌های توی عکس‌هات رو پیدا می‌کنه و می‌ذاره باهاشون استایل‌های مختلف بسازی.


@Digiai
با این پرامپت عکستو ببر به حال‌وهوای خفن و نوستالژیک شب‌های دهه ۲۰۰۰

Use the same person as the reference image, identity preserved, recognizable facial features and natural facial proportions. Create a close-up Y2K nightlife portrait with a mysterious, playful expression, head slightly tilted, eyes looking at the camera or just to the side, mouth relaxed, pale flash-lit face, messy after-party energy. The subject should look like a stylish nocturnal club figure, vampire-coded but not fantasy cosplay.

[STYLING]

Neutral indie sleaze streetwear: black tank top or fitted dark t-shirt, open black shirt or worn leather-like jacket, layered silver necklaces, simple rings, belt, low-rise denim or dark trousers. Hair slightly messy or damp from the club. Styling should adapt naturally to the person and avoid forcing a masculine or feminine silhouette.

[COMPOSITION]

Vertical 4:5 portrait, close chest-up or waist-up framing, old digital camera selfie-adjacent angle without a visible phone. Slightly off-center composition, cramped club bathroom or stairwell, dirty mirror edge, tiled wall, scratched metal, sticker-covered surface, dark doorway behind the subject. Background should be blurred but still recognizable as nightlife interior.

[RENDER STYLE]

2007 MySpace profile photo, indie sleaze club photography, old compact digital camera, harsh flash, high contrast, low fidelity internet image, dirty nightlife editorial, imperfect candid fashion shot.

[LIGHTING]

Harsh direct flash on the face and chest, overexposed whites, deep black shadows, cold green-blue bathroom light, slight red tint in the shadows, shiny highlights on jewelry and hair. Flash should feel cheap and intense.

[COLOR PALETTE]

Black, cold white, dirty blue, sickly green, deep burgundy shadows, desaturated skin, faded red accents, no clean pastel colors.

[IMAGE DEGRADATION]

Digital noise, JPEG artifacts, dirty lens, motion blur at the edges, slight red-eye feeling, crushed shadows, blown highlights, chromatic aberration, dusty frame, low-resolution social media upload texture.

[ATMOSPHERE]

Dark, sexy without being explicit, playful, nocturnal, messy, nostalgic, underground, early social media profile photo energy, lost MySpace archive, club bathroom after midnight.

[AVOID]

Changing the reference identity, changing facial proportions, literal vampire fangs, blood, fantasy costume, over-defining gender, gender transformation, polished modern nightclub photo, luxury campaign, clean studio background, outdoor daylight, warm golden light, perfect skin retouching, readable text, logos, watermark, ultra sharp details, distorted face, blurry eyes.


🎨  Make your photo
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
این پرامپت جدیدا خیلی ترند شده.

UPLOAD A REFERENCE IMAGE BEFORE GENERATING.

MAIN PROMPT
Using the uploaded photo as the primary reference, transform ONLY the main subject into a charming oversized-head hand-drawn cartoon caricature. The head must be dramatically exaggerated, approximately 45–60% of the character’s visual height, with a compact, much smaller body. Preserve the subject’s recognizable identity and defining characteristics while keeping the original photograph and environment fully recognizable.

FORMAT LOCK
Vertical 3:4. Preserve the original framing, camera angle, perspective, depth, subject placement, pose, orientation, and composition. Keep the photographic environment unchanged.

STYLE TRANSFER
Create a naïve children’s-book caricature with a deliberately huge, subject-specific head, enlarged forehead and cheeks, tiny simplified body, short limbs, small hands and feet, and a cute humorous proportion. Adapt the head shape, silhouette, hairstyle, hairline, facial hair, ears, beak, hat, helmet, or other defining features specifically to the original subject. Never use a generic circular head.

DETAIL & COLOR
Preserve facial structure, expression, skin tone, hairstyle, facial hair, clothing, accessories, patterns, logos, shoes, jewelry, and distinctive details. Use simple dot/oval eyes, tiny simplified nose, curved mouth, subtle cheeks when appropriate, soft natural colors, visible colored-pencil strokes, rough hatching, cross-hatching, uneven fills, overlapping strokes, imperfect edges, and subtle paper texture.

COMPOSITION LOCK
Transform ONLY the main subject. Keep the entire background photorealistic, including architecture, landscape, furniture, vehicles, scenery, lighting, depth, perspective, and atmosphere. Integrate the illustrated character naturally into the original scene with matching position, perspective, lighting direction, and subtle grounding shadows.

STYLE
Loose hand-drawn ink and colored-pencil caricature, charming, whimsical, naïve, expressive, handmade, slightly imperfect. Thin-to-medium organic black outlines, rough pencil texture, spontaneous sketch marks, simplified clothing, exaggerated oversized head, tiny body. The contrast between the realistic photograph and illustrated subject should be intentional and visually striking.

NEGATIVE PROMPT
Normal head proportions, small head, generic head shape, generic cartoon character, identical head shape across subjects, photorealistic subject, cartoonized background, fully illustrated scene, anime, vector art, 3D CGI, Pixar, Disney, glossy digital rendering, plastic texture, smooth gradients, polished graphics, altered identity, changed hairstyle, changed clothing, changed pose, distorted facial features, excessive facial detail, oversized body, realistic anatomy, unnecessary background changes.

ASPECT RATIO: 3:4


🎨  Make your photo
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
This media is not supported in your browser
VIEW IN TELEGRAM
کثافت آشغال صد دفه گفتم اسم بابای منو به زبون نیار نسخه یوسف و زلیخا.

@Digiai
با این پرامپت میتونی ببینی اگه بینیتو عمل کنی چجوری میشه.

Edit the uploaded photo to create ONE photorealistic cosmetic nose-reshaping preview of the same person. Generate the edited image directly.
The nose MUST look visibly reshaped compared with the original. Aim for a moderate, clearly noticeable transformation that remains natural and proportionate to this specific face. Do not return an unchanged or barely altered nose.
Adapt the changes to the visible nose: smooth a prominent bridge hump if present, refine a broad or rounded tip, moderately reduce excessive apparent width, and gently adjust a downward-pointing tip if visible. Select only changes relevant to the photograph; do not apply every modification automatically. Keep realistic nostril shapes, natural contours, and believable proportions. Avoid an extremely small, pinched, deeply scooped, or sharply upturned nose.
Change ONLY the nose and the immediately surrounding shadows needed to integrate the edit. Preserve the exact same person, all other facial features, skin texture, expression, hairstyle, camera angle, lighting, clothing, background, and framing. Do not beautify the rest of the face.
Before delivering, compare the original and edited nose. If the reshaping is not clearly noticeable at normal viewing size, revise the nose edit until it is visible without exaggeration.
This is an aesthetic simulation, not a medical assessment or a prediction of an achievable surgical outcome. Do not claim to be a surgeon.
Output one edited portrait, without a collage or text overlay. Add this short caption separately:

«شبیه‌سازی ظاهری؛ نتیجهٔ واقعی جراحی ممکن است متفاوت باشد.»
If image editing is unavailable, say so clearly instead of returning the original photo or claiming it was edited.


توجه: سبک و نتیجه عمل بینی از دکتری به دکتر دیگه فرق داره و مدل‌های مختلفی برای جراحی وجود داره. این پرامپت فقط یه شبیه‌سازیه و نتیجه واقعی عمل می‌تونه متفاوت باشه.


🎨  Make your photo
Please open Telegram to view this post
VIEW IN TELEGRAM
ما آخرین نسلی هستیم که یادمونه دنیا قبل از هوش مصنوعی چه شکلی بود.