Package vision_models (1.71.1)

model = ImageCaptioningModel.from_pretrained("imagetext@001")
image = Image.load_from_file("image.png")
captions = model.get_captions(
    image=image,
    # Optional:
    number_of_results=1,
    language="en",
)

model = ImageGenerationModel.from_pretrained("imagegeneration@002")
response = model.generate_images(
    prompt="Astronaut riding a horse",
    # Optional:
    number_of_images=1,
    seed=0,
)
response[0].show()
response[0].save("image1.png")

model = ImageQnAModel.from_pretrained("imagetext@001")
image = Image.load_from_file("image.png")
answers = model.ask_question(
    image=image,
    question="What color is the car in this image?",
    # Optional:
    number_of_results=1,
)

model = ImageTextModel.from_pretrained("imagetext@001")
image = Image.load_from_file("image.png")

captions = model.get_captions(
    image=image,
    # Optional:
    number_of_results=1,
    language="en",
)

answers = model.ask_question(
    image=image,
    question="What color is the car in this image?",
    # Optional:
    number_of_results=1,
)

model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding@001")
image = Image.load_from_file("image.png")
video = Video.load_from_file("video.mp4")

embeddings = model.get_embeddings(
    image=image,
    video=video,
    contextual_text="Hello world",
)
image_embedding = embeddings.image_embedding
video_embeddings = embeddings.video_embeddings
text_embedding = embeddings.text_embedding