1. Open Gemini 2. Upload your photo 3. Enter this prompt 4. Generate 5. Change the pose
Here are 10 best prompts (PART 2)🧵
1/ Prompt:
A 4K ultra-realistic portrait of a young girl, framed from the chest up (not full body), designed for Instagram story or profile picture. The background is a luxurious Persian red carpet design (only behind her, not on the ground). Sunlight shines from one side,casting natural warm light across half of her face. She is wearing an elegant dress inspired by Persian carpet patterns,with authentic Iranian colors and motifs. Her facial features remain unchanged.She is holding a Persian cat in her hands
2/ Prompt:
Create a photo-style line drawing / ink sketch of a face identical to the uploaded reference image — keep every facial feature, proportion, and expression exactly the same.
Use green and white ink tones with intricate, fine line detailing, drawn on a notebook-page style background.
Show a right hand holding a pen and an eraser near the sketch, as if the artist is still working.
3/ Prompt:
CINEMATIC STREET PHOTOGRAPHY, STYLISH YOUNG WOMAN IN MOTION, URBAN ENVIRONMENT, MOTION BLUR EFFECT. BLURRED PEDESTRIANS PASSING BY, SHALLOW DEPTH OF FIELD, NATURAL OVERCAST LIGHTING, SOFT PASTEL TONES, EDITORIAL FASHION PHOTOGRAPHY, CANDID MOMENT, DYNAMIC MOVEMENT, FILM AESTHETIC, MUTED COLORS
4/ Prompt:
4K Ultra-HD self portrait of individual (face same as reference image),wearing outfit as reference,taken through the reflection of an round mirror with a thin black border,one holds a gold iphone in left hand,while the right hand chin as style.Afternoon sunlight streams in
through the window on the right,creating dramatic shadows that highlight the face. The image has a vintage,nostalgic aesthetic,
5/ Prompt:
Cinematic portrait of the man in the picture (preserve 100% facial details of this man), vintage classroom. The camera is shot from a distance, with a small section of the chair's back visible in front, as if the photographer was taking the portrait discreetly or in a quiet moment. Soft, golden-yellow lighting reflects from a small window or gap in the right wall, forming diagonal lines of light that fall directly on the man's face, creating a dramatic and emotional contrast. The man sits alone in a chair, his feet resting on the desk, with a relaxed and cool expression, as if lost in thought. He wears an oversized army black Sweater, cream-colored cargo pants, Converse sneak-ers, and red headphones. He has a bag hanging from the chair, but it blends harmoniously with the warm light surrounding him. Behind him is an off-white wall with sticky notes labeled "beingbb" notices duty schedules, and So on, and a photo at the top. There are also a few decorations or furnishings typical of a college classroom. Reinforcing a nostalgic and contemplative feel, like a frozen moment in time. Soft golden hues of light blend with the dark shadows in the room, creating a quiet, warm, and slightly wistful atmosphere, reminiscent of a scene from a Japanese indie film at dusk or early morn-ing. The overall atmosphere suggests an intimate, introspective moment in silence. All image elements are rendered without bokeh, with even sharpness from foreground to background. The visual texture contains noticeable noise and grain, reminiscent of the results of analog 35mm film cameras like the Canon AE-1 or retro digital simulations using the Fujifilm X100V with "Classic Chrome" film simula-tion. Possible camera settings: ISO 1600, f/5.6 aperture, 1/60s shutter speed, with a warm white balance to maintain the natural golden light in the room. The grain effect can come from ISO 400 film or the digital grain feature intentionally activated to add cinematic character and nostalgia.
6/ Prompt:
Without changing my facial features and face. It should be look like realistic. remove my hearings. Created me the same page on attachment 100% unchanged. A full-body studio portrait of a handsome young East Asian woman sitting on the floor in front of a light purple backdrop. she is wearing a cozy, oversized lavender chunky-knit sweater, white skirt, and white socks. she is affectionately hugging a large Sanrio Kuromi plushie and looking at the camera with a gentle expression. The background is decorated with playful, hand-drawn purple doodles and text (like "R" "RAVYA," paper airplanes, and flowers), creating the style of a K-pop photocard or fanzine cover. The lighting is bright and soft, enhancing the cute and affectionate mood. I want exact same face as I uploaded no alteration 100 percent.
7/ Prompt:
Portrait of a chic young woman A 100% face alignment to uploaded reference image ' sitting casually indoors against a white shelf filled with white ceramic cups. She wears a classic black beret, her long black hair flowing down her back. Her face is elegant with a calm expression, slightly raised eyebrows, and natural-colored lips. She wears an oversized gray-and-white striped shirt, tucked into black shorts. Her right hand holds a pair of sunglasses close to her face, while her ears are adorned with stacked hoop earrings.The photo's minimalist fashion editorial style, with soft lighting, emphasizes a modern, classy, and stylish feel.
8/ Prompt:
Studio portrait, Renaissance style, soft and warm lighting
with a golden glow, dramatic light coming from above, creating soft shadows.The person is positioned slightly facing to the side, with his head tilted and his gaze directed at the camera, conveying a contemplative and dreamlike expression. She delicately holds a small bouquet of white or cream roses with long stems, with some visible green leaves, near her face, as if she were Smelling the flowers. the dress is a cream or off-white Victorian/ Regenal style dress with a shoulder-to-shoulder neckline and puff sleeves with lace details and ruffled cuffs. A necklace of pearls adorns the neck and falls elegantly on the bust. The hair is long, wavy, and loose, falling on shoulders and chest. The background is a draped fabric, in neutral and warm tones like beige or light brown, with a soft texture, adding depth and a classic touch. The depth of the field is shallow, focusing on the person and the flower background slightly blurred. The color palette is monochromatic, dominated by warm, soft and earthy tones. The image quality is photographic, with a touch of timeless elegance, like a classic oil painting. "(Keep 100% all my facial and physical traits)
9/ Prompt:
A 100% face alignment to uploaded reference image candid portrait of a young woman standing at a subway station, wearing a loose black jacket and carrying a black backpack. She has long straight black hair, natural makeup, and is listening to music with white earphones. Her pose is casual with one hand on her waist, looking slightly to the side with a thoughtful expression.The background shows a modern metro train with glass doors, a subway route map above, and yellow safety lines on the floor. The atmosphere is urban, realistic, and cinematic with soft lighting
10/ Prompt:
Ultra-realistic photo of a young woman (based on 1st uploaded photo), She has 155cm tall and 54kg weight lounging outdoors on a sunny terrace with tropical plants and bohemian decor in the background. She is sitting casually wearing the outfit attached. Put her bag on the couch. Her hair was pinned out The pose is casual like a model with a soft expression. Natural daylight highlights her skin with a smooth, glowing finish.
If you enjoyed the thread:
1. Follow me @eyishazyer for more AI content.
2. Subscribe my newsletter to discover the key developments, challenges, and opportunities in The AI Foreground.
Here’s the ultimate resource to master its creative editing power
20+ Nano-Banana use cases, each with the prompt, input, and output side by side: (Part 2)
Case 1: OOTD Outfit(by @302.AI)
input: Need to upload a person image and clothing image
PROMPT:
Choose the person in Image 1 and dress them in all the clothing and accessories from Image 2. Shoot a series of realistic OOTD-style photos outdoors, using natural lighting, a stylish street style, and clear full-body shots. Keep the person's identity and pose from Image 1, but show the complete outfit and accessories from Image 2 in a cohesive, stylish way.
Case 2: Character Pose Modification(by @arrakis_ai)
input: Need to upload reference image
PROMPT:
Have the person in the picture look straight ahead
1. Open Gemini 2. Upload your photo 3. Enter this prompt 4. Generate 5. Change the pose
Here are 10 best prompts (PART 1)🧵
2. Prompt:
A high-resolution black and white portrait of a girl wearing a sharp black turtleneck and chic small gold earrings, along with a Korean bun. She stands confidently in a minimal studio setting, slightly to the side. Dramatic studio lighting creates bold geometric shadows on her face and background with strong cross beams of light. Cutting through the shadows, her expression is calm, introspective, and slightly distant. The image has a cinematic atmosphere.
3. Prompt:
Take a picture with a Polaroid camera. The photo should look like a normal photo, without any clear subject or props. The photo should have a slight blur a a consistent light source. Such as a flash from a dark room, spread throughout the photo. Do not change the faces. Replace the background behind the two people with a white curtain. (With the guy hugging girl) Change outfits with matching couple.
At the same time, you also gain access to ChatLLM, which is part of Abacus AI's ecosystem.
This tool allows you to access ChatGPT, DeepSeek, Grok, Gemini, Llama, Claude, Recraft, Ideogram, Flux, Kling AI, Runway, and more from a single place.
Here’s the ultimate resource to master its creative editing power
60+ Nano-Banana use cases, each with the prompt, input, and output side by side: (Part 1)
Case 1: Illustration to Figure(by @ZHO_ZHO_ZHO)
input: Need to upload a reference image as the object for generating the figure
PROMPT → 'turn this photo into a character figure. Behind it, place a box with the character's image printed on it, and a computer showing the Blender modeling process on its screen. In front of the box, add a round plastic base with the character figure standing on it. set the scene indoors if possible'
Case 2: Generate Ground View from Map Arrow(by @tokumin
input: Need to upload a Google Maps image containing a red arrow
PROMPT → 'draw what the red arrow sees
/
draw the real world view from the red circle in the direction of the arrow.'
Here's are true reasons why hallucinations occur, as shown in the paper, along with 6 solutions🧵
1. AI is trained in such a way that it cannot say
"I don't know"
The biggest cause of hallucinations lies in the AI's training method itself.
In the current evaluation systems, even if the answer is incorrect, guessing provides a higher score than answering "I don't know," so the AI ends up learning to actively lie (bluff).
2. "Accuracy Supremacy"
Encourages Lying Benchmarks that measure AI performance basically only look at whether the answer is correct or incorrect.
Answering "I don't know" gets 0 points, so even in uncertain cases, guessing yields a higher expected value.
This "test-soaked" state has been producing AIs that confidently lie.