Builders can now entry Imagen 3, Google’s state-of-the-art picture era mannequin, by the Gemini API. The mannequin will likely be initially accessible to paid users, with a rollout to the free tier coming quickly.
Imagen 3 excels in producing visually interesting, artifact-free photographs in all kinds of kinds from hyperrealistic photographs to impressionistic landscapes, summary compositions to anime characters. Improved immediate following makes it simple to transform nice concepts into high-quality photographs. General, Imagen 3 achieves state-of-the-art efficiency on the number of benchmarks. Imagen 3 achieves this whereas being priced at $0.03 per picture on the Gemini API, with management over side ratios, the variety of choices to generate, and more.
To assist fight misinformation and misattribution, all photographs generated by Imagen 3 embrace a non-visible digital SynthID watermark, figuring out them as AI-generated.
See Imagen 3 in Motion
The gallery under highlights Imagen 3’s capabilities throughout a variety of kinds.
Immediate: Group of individuals wanting blissful, pure gentle, 8k
Immediate: Hyperrealistic portrait of an individual wearing Twenties flapper style, classic model, black and white {photograph}, elegant pose, 8k
Immediate: Think about a close-up of a classic watch. Generate a sensible depiction with an in depth mechanism
Immediate: Impressionistic panorama portray of a sundown over a discipline of sunflowers, vibrant colours, thick brushstrokes, impressed by Monet
Immediate: A surreal dreamscape that includes a large tortoise with a lush forest rising on its again, floating by a starry sky, glowing mushrooms, bioluminescent vegetation, ethereal ambiance
Immediate: Life-style picture of freshly roasted espresso beans spilling out of a burlap sack onto a country wood desk, steam rising from a close-by cup of espresso, ‘Awaken Your Senses’ is written on the cup in cursive, heat and welcoming ambiance, morning daylight, product images
Immediate: Hyperrealistic portrait of a girl with piercing blue eyes, laughing, freckles, dramatic lighting, detailed pores and skin texture, 8k
Immediate: A panoramic view of an imposing mountain vary at daybreak.
Immediate: Present a scene from a recreation the place the participant must discover a particular object by wanting into drawers in a messy desk.
Immediate: A cityscape painted within the model of Van Gogh, with swirling brushstrokes and vibrant colours.
Get Began with Imagen 3 within the Gemini API
This Python code snippet demonstrates tips on how to generate a picture with Imagen 3 utilizing the Gemini API.
from google import genai
from google.genai import varieties
from PIL import Picture
from io import BytesIO
shopper = genai.Consumer(api_key='GEMINI_API_KEY')
response = shopper.fashions.generate_images(
mannequin='imagen-3.0-generate-002',
immediate='a portrait of a sheepadoodle carrying cape',
config=varieties.GenerateImagesConfig(
number_of_images=1,
)
)
for generated_image in response.generated_images:
picture = Picture.open(BytesIO(generated_image.picture.image_bytes))
picture.present()
You may discover extra prompting recommendation and picture kinds within the Gemini API developer docs, with additional particulars obtainable on scores, methodology, and efficiency enchancment in Appendix D of our up to date technical report.
We’re excited to take step one of increasing availability of our generative media fashions into the Gemini API and plan to make extra obtainable within the close to future in order that builders can bridge generative media and language fashions collectively.
