Relevant learning activities, right in #GoogleClassroom. 📚
Now, all educators and students can collaborate with Gemini and leverage class materials to draft tailored resources to support deeper learning - all in a secure environment.
See what’s new: https://t.co/Lxond8MEvl
GPT image 2 via chatgpt
Prompt:
Create a clean side-by-side composition on a light gray seamless studio background.
Left Side:
Ultra-realistic full-body portrait of the girl standing in a cute playful pose with one leg lifted behind her, smiling gently at the camera. She is wearing a modest, fully covered outfit consisting of a fitted long-sleeve chocolate brown knit top with a high neckline, a cream A-line midi skirt below the knees, white ankle socks, and white sneakers. She carries a pastel blue crossbody bag with a small teddy bear keychain. Natural body proportions, realistic fabric texture, soft studio lighting, professional fashion photography.
Right Side:
A cute chibi anime version of the same girl with identical hairstyle, facial features, outfit, pose, blue crossbody bag, teddy bear keychain, white socks, and sneakers. Large sparkling eyes, soft blush, adorable smile, high-quality anime illustration with clean outlines and smooth shading.
Background:
Minimal light gray studio backdrop with hand-drawn black doodle accents around both characters, including motion lines, sparkle marks, and playful sketch elements.
Lighting:
Soft diffused studio lighting, even illumination, realistic skin tones, gentle shadows, premium editorial photography look.
Camera:
Canon EOS R5, 50mm lens, f/2.0, eye-level composition, shallow depth of field, ultra-sharp focus.
Quality:
Ultra-realistic, photorealistic, 8K, HDR, highly detailed, realistic skin texture, authentic fabric details, clean composition, premium studio portrait.
Aspect Ratio:
--ar 4:5
Negative Prompt:
revealing clothes, sleeveless, crop top, deep neckline, cleavage, transparent fabric, mini skirt, shorts, lingerie, blurry, low quality, extra fingers, distorted anatomy, watermark, text, logo.
GPT image 2 via chatgpt
Prompt:
Create a creative 3×3 collage featuring the same woman from the uploaded reference image. Maintain 100% facial identity consistency across all nine panels. Preserve her exact face, hairstyle, hair color, skin tone, eyes, eyebrows, nose, lips, body proportions, age, and expression.
She should be clearly visible in every scene (not tiny or far away), occupying about 35–50% of each frame.
Wardrobe Rule: In every panel, the woman must wear a different stylish outfit. No outfit should be repeated. Use modern summer clothing such as elegant dresses, casual jeans with tops, skirts, jumpsuits, coordinated sets, linen outfits, floral dresses, oversized shirts, or chic casual wear. Each outfit should have a different color, style, and accessories while remaining tasteful and fashionable. Only the clothing changes; the woman's facial identity, hairstyle, body proportions, and overall appearance must remain exactly the same.
Style: realistic miniature photography combined with whimsical black-and-white hand-drawn doodle illustrations on a soft white fabric background with gentle folds.
The 9 scenes should include:
Walking across a giant pencil bridge.
Climbing a tall stack of oversized books.
Surfing on a giant spoon through splashing milk with playful doodle elements.
Sitting on a flying paper airplane above a sketched city.
Riding a cute giant snail.
Sleeping comfortably inside a large coffee mug with steam.
Swinging on oversized headphones in the sky.
Standing inside the center of a hand-drawn maze, looking upward.
Sitting on a giant Rubik's Cube surrounded by floating math symbols.
The woman must remain the main subject in every panel, with a medium-full body view so her face is easily recognizable. Keep the lighting soft and natural, realistic shadows, high detail, ultra-sharp focus, premium editorial photography, clean white background, seamless collage layout, playful imagination, photorealistic quality, 8K.
Gemini Omni Flash can swap objects, change environments, and make targeted edits to existing videos using simple text prompts.
To try this workflow, link below 👇
Gemini Omni Flash is now in ComfyUI via partner nodes.
Google's state of the art model with physics and video editing capabilities is now inside the world's most strongest generative AI workflow engine.
Click the link below for the workflows 👇
Millions of people are trying out new workflows pairing Canva and AI assistants.
The latest unlock? Whether you're coming from Gemini, Claude, ChatGPT, or Microsoft Copilot, you can use Canva's Magic Layers to unlock every visual element as a separate, editable layer to remix, refine, and make your own.
If only Art came to life (Part. 3)
So excited to finally share Part 3 of this series… and here’s the best part: you can now recreate this concept in just a few clicks with Apps, exclusively with @Artlist_io ✨
Tutorial 👇
GPT Image 2 On ChatGPT
Prompt:
A playful, high-key studio portrait of [subject] running joyfully across a seamless light gray background, captured mid-stride with one leg lifted and a wide genuine smile. The subject wears a casual oversized outfit with soft neutral tones (or vibrant colors), creating a dynamic sense of motion. Behind them, a simple black hand-drawn cartoon stick figure grabs and stretches the back of their shirt, making the fabric appear elastically pulled as if trying to stop them. The doodle character is integrated naturally into the scene with expressive motion lines and a humorous facial expression. The subject holds a fun prop (such as a dinosaur toy, oversized lollipop, teddy bear, or balloon), enhancing the playful storytelling. Minimalist composition, clean studio lighting, soft shadows, ultra-sharp focus, realistic skin texture, vibrant yet natural colors, whimsical editorial photography, premium children’s fashion campaign aesthetic, highly detailed, photorealistic, 8K.
gemini omni flash is here: our high-quality, cost-efficient model for video generation and conversational editing
designed to support multimodal workflows, it enables you to refine videos using natural language and simple prompting
start building with it today via ai studio and the gemini api
GOOGLE 🔥: A new Nano Banana 2 Lite image generation model is on the horizon!
> "Introducing Nano Banana 2 Lite for ultra-fast, cost-efficient image generation, and Gemini Omni Flash for powerful video creation with conversational, step-by-step editing"
Created with GPT Image 2.0 on ChatGPT
Prompt: Create an ultra-realistic, high-resolution humorous portrait of a famous football-style athlete with an exaggerated oversized head and a small, realistic body, sitting exhausted on the floor and leaning against a plain light-gray wall. The subject has a tired, lifeless expression with half-closed eyes, slightly open mouth, messy yet stylish short dark hair, subtle facial stubble, and realistic skin texture with visible pores and natural imperfections.
He wears a light gray hoodie, matching gray shorts, and white ankle socks. His legs are stretched out casually, arms resting loosely on his thighs, conveying complete exhaustion and zero energy.
On the wall beside him is a standard electrical outlet with a white charging cable plugged into it, humorously implying that he needs to recharge like a phone. Above his head floats a clean smartphone-style 1% battery icon with a nearly empty battery outlined in white and a tiny red charge bar, reinforcing the "out of battery" concept.
The setting is a modern indoor room with soft beige walls, gray carpet, a large window with natural daylight entering from the left, and neutral-colored curtains. Lighting is soft, cinematic, and natural, creating gentle shadows and realistic depth.
Style: ultra-photorealistic, editorial-quality, hyper-detailed skin, realistic fabric textures, shallow depth of field, HDR, 8K, DSLR look, premium humor photography, clean composition, centered framing, subtle warm color grading, highly shareable, stop-scrolling, viral social media aesthetic.
GPT image 2 via chat Gpt
Prompt :
Preserve only 100% the original face from the reference photo. The hair, clothing, accessories, pose, and background should be created based on the prompt.
Create an image that perfectly preserves the facial features of the uploaded reference photo. A hyper-realistic creative street scene featuring a giant curved-edge 3D anamorphic billboard mounted on the exterior wall of a modern building beside a bustling city intersection.
Inside the billboard stands a woman/man wearing a yellow T-shirt printed with "[ Your Name ]", along with an Apple Watch on her wrist. One of her hands breaks through the billboard's boundary, creating a stunning 3D illusion, while holding a perfectly scaled miniature version of herself.
The miniature version wears a red "[ Your Name ]" T-shirt, blue ripped jeans, red-and-white Nike Air Jordan 1 sneakers, and a red Apple Watch, while riding a miniature pink electric scooter placed naturally on the street beside the billboard.
Inside the billboard, include bold luxury-style typography.
The main headline should read "[ Your Name ]", with the subtitle below displaying "[ Write anything you want ]".
The overall composition should blend luxury fashion advertising with playful anamorphic illusion art, combining ultra-realistic rendering with trendy modern aesthetics.
The background features a lively urban street filled with traffic and pedestrians, illuminated by realistic natural lighting with crisp, highly detailed textures, creating a vibrant contemporary city atmosphere while maintaining the original aspect ratio.
Nano banana pro
Prompt:
A stunning double exposure watercolor portrait art of a young woman with dark brown shoulder-length hair, hazel-green eyes, natural makeup, soft smile, wearing a royal blue button-up casual shirt. Large close-up face portrait blended seamlessly with a full-body shot of the same woman wearing sunglasses, black slim pants, white sneakers and a wristwatch, standing in a relaxed pose with one leg crossed. Background is pure white with dramatic royal blue and cobalt watercolor ink splashes, blooms, and drips cascading down. Watercolor paint splatters in varying shades of blue — cobalt, indigo, cerulean — scattered across the white canvas. Paint drips running vertically downward. The portrait and full-body figure emerge organically from the watercolor splashes. Ultra-realistic photographic face with painterly watercolor body transition. High detail, sharp focus on face, soft artistic edges blending into watercolor. Editorial art style, white background, blue ink wash aesthetic.
Made with GPT image.2 on chatgpt
Prompt 👇
Create a premium ultra-realistic studio portrait of the same adorable toddler duplicated three times, with every clone preserving the exact same face, hairstyle, skin tone, joyful smile, body proportions, and identity. Arrange the three identical toddlers in a stylish fashion composition. The center toddler is walking confidently toward the camera with a cheerful smile, while the left and right toddlers stand in relaxed poses with one hand in their pockets, both wearing black sunglasses.
All three toddlers wear matching premium black button-up shirts with rolled sleeves, slim-fit white trousers, luxury silver wristwatches, and clean white sneakers. Their hair is thick, voluminous, and side-swept with a fashionable texture.
The background is a dramatic luxury black studio with glossy reflective flooring, cinematic warm spotlight bokeh, and large frozen white milk splash effects behind the toddlers. Ultra-realistic lighting, premium fashion editorial styling, shallow depth of field, realistic skin texture, HDR, 8K, DSLR quality, Canon EOS R5, 85mm lens, f/1.8, masterpiece, luxury children's fashion campaign, photorealistic, no text, no watermark, no logo.
Negative Prompt: low quality, blurry, cartoon, anime, CGI, extra limbs, duplicate face errors, bad anatomy, distorted body, deformed hands, watermark, logo, text, cropped, oversaturated, noise, low resolution.