This photo looks like a $5,000 commercial shoot：lighting, composition, even the model.
Here’s the twist: it wasn’t shot by a photographer at all. It was generated in seconds by Google’s new Gemini model.
I’ve spent the past week testing it, and the results convinced me: AI product photography just crossed a new threshold.
1. Photo to Figurine Conversion
The figurine effect has gone viral across social platforms, and for good reason.
The process is straightforward: upload any photo and describe what you want.
Prompt: Transform this photo into a character figurine. Behind the figurine, place a packaging box featuring the character's image. Display the Blender modeling process on a computer screen. In front of the packaging box, place a circular plastic base for the character figurine to stand on. Make the PVC material look clear and bright, and set the scene indoors with bright, moderately saturated lighting.
I also tested it with an anime character:
2. Product Scene Generation
Prompt: Product promotional image. Place the product in a vibrant background of green moss and other plants, creating a natural, fresh atmosphere. The composition should be rich with elements. Behind the product, place a fallen log on the ground. Around the product, add fresh chicken breast, avocado, salmon slices, and a wooden bowl filled with freeze-dried chunks. Include a cat nearby. Use soft, natural lighting that mimics sunlight to make the overall scene look lively and textured, highlighting the natural, healthy qualities of the pet food. Medium shot composition, focusing primarily on the product.
The quality competes directly with professional photography:
Prompt: Product promotional image. Place the product among vibrant green moss and plants. The ground should be covered with emerald moss, with blue sky and white clouds in the background. Center the cat food packaging, with fresh chicken placed on a tree stump beside the packaging. Surround the scene with pumpkins, pears, blueberries, and other ingredients. Use bright, soft lighting that mimics clear natural sunlight to emphasize the natural nutrition of the cat food. Make the composition rich yet harmonious.
Next, I tested it with snack packaging:
Prompt: Product promotional image. Two product packages placed on vibrant emerald moss grassland, shot from above. The center features a wooden tray on a casually arranged, wrinkled tablecloth with snack packaging. Around it, scatter over a dozen fresh strawberries, blueberries, cookies, and strawberries. The background features emerald moss, with a yellow tablecloth spread under the tray. Use bright, soft lighting that simulates clear natural sunlight, with alternating light and shadow. Surround with emerald moss and fern plants for an overall fresh, healing atmosphere full of life, with fresh and vibrant color contrast.
Prompt: Product promotional image. Two product packages placed on vibrant outdoor emerald moss grassland. The center features a wooden tray on a casually arranged, wrinkled tablecloth with snack packaging. Around it, scatter over a dozen fresh strawberries, blueberries, cookies, and strawberries, plus a flower basket filled with fresh flowers. The ground is emerald moss, with a large beige tablecloth spread under the tray, covered with various fruits, snacks, and drinks. An Asian woman in a yellow dress and a child in white clothes kneel on the tablecloth, smiling at the product. Use bright, soft lighting that simulates clear natural sunlight with alternating light and shadow. Surround with emerald moss and tropical plants, with blue sky and white clouds in the background. Create an overall fresh, healing atmosphere full of life with fresh and vibrant color contrast. Bright lighting, close-up composition, high saturation, overhead perspective.
The lighting effects are remarkable:
Here's how it handles kitchen appliances:
Prompt: Product commercial promotional image. Place the product in a cozy home scene (wooden cabinets, green plants, decorative paintings, water cups, etc.), with the product prominently featured.
Prompt: Product commercial promotional image. Place the product in a cozy home scene (wooden cabinets, green plants, decorative paintings, water cups, etc.), with a Western female model drinking coffee on the sofa behind, keeping the product prominently featured.
Prompt: Place the product in a cozy home leisure scene with decorative painting background wall. On the tabletop, include a water kettle, glass cups filled with tea, next to a female model using a laptop computer, along with books, white pen holders, cake, green plants, and other elements. Use soft side lighting to create alternating light and shadow effects. Bright indoor lighting highlights the exquisite tea set and comfortable atmosphere.
Testing with home appliances like air purifiers。
Prompt: Place the product in a cozy home scene, a warm and comfortable living room with original wood flooring and a light beige circular rug. A woman in a white sleeveless dress kneels on the rug playing with a cat, smiling. The background features a brown sofa, wooden cabinets, decorative paintings, and multiple green plants. Floor-to-ceiling windows with greenery outside, large floor-to-ceiling windows. Alternating light and shadow create a natural, life-filled atmosphere. High-definition image quality with rich details, creating an overall high-end atmosphere with light-dark contrast. Air purifier product commercial promotional image, moderate saturation, with the product prominently featured.
3. Internal Product Structure Display
If you've worked in consumer electronics (computers, communications, consumer goods), you know how valuable exploded diagrams are for marketing. Here's how Gemini handles technical visualization:
Prompt: Ultra-detailed product exploded view, metallic parts and electronic components floating in mid-air, neatly arranged, with internal structure clearly visible, featuring futuristic technological aesthetics, 8K resolution, soft cinematic lighting, highly realistic.
Prompt: Transform product image into product exploded view using horizontal linear composition, with metallic parts and electronic components suspended in arrangement, internal structure clearly visible. Overall cool-toned tech aesthetic, primarily deep gray and silver-black. Metallic parts show delicate luster and texture. Lighting uses soft cinematic lighting from the side to highlight the three-dimensional feel and precise details of each component, creating a futuristic technological aesthetic atmosphere.
4. Multi-Image Fusion
For this test, I combined both the snack packaging and water kettle in a single scene
Prompt: Place 2 products in a bright indoor environment background, creating a warm and comfortable office breakfast atmosphere with rich compositional elements. Two hands using a laptop (screen displaying webpage content), with a breakfast plate nearby (knife and fork, croissant, fried egg, vegetables), a cup of hot water, scattered red dates, plus a white pen holder (containing stationery) and stacked books, green plants. Lighting is soft natural light streaming in from the left window, creating subtle light and shadow layers, illuminating desktop items and hand movements. Overall creates a comfortable, lifestyle feeling with high saturation.
5. Element Replacement and Modification
Taking the previous image, I made several modifications。
Prompt: Replace the person in the image with a female, change her clothing, replace the table with marble material, and add multiple green plants indoors.
Character consistency is crucial for brand work. Here's how well it maintains the same person across different scenarios:
Prompt: Have the person in the image stand leaning against a walnut wood counter, holding a hair dryer to blow-dry hair, in a simple home setting.
Prompt: Have the person in the image sit in a lounge chair holding a hair dryer to blow-dry hair, in a warm and simple home setting.
Across different poses and settings, the character consistency remains solid.
After extensive testing, here are my key findings:
1. Consistency is dramatically better
Both character and product consistency across iterations has improved significantly.
2. Professional-grade results
The product imagery quality matches expensive commercial photography.
3. More reliable outputs
Fewer failed generations and random results (what gamers call "gacha" mechanics).
Quick troubleshooting tip:
Wondering why output dimensions vary? Gemini matches your input image's aspect ratio. Upload a square photo, get square results. Upload landscape, get landscape output.
With Gemini, consistency is finally here, quality rivals commercial studios, and iteration is faster than ever.
To me, this feels like the moment stock photography and commercial shoots face their first real challenger.
The only question: will you be an early adopter who saves time and budget, or will you wait until AI dominates the creative pipeline?
