CohereForAI/aya-vision-8b · Multi image inference

Yes it does! here's an example from the doc:
from transformers import AutoProcessor, AutoModelForImageTextToText
import torch

model_id = "CohereForAI/aya-vision-8b"

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
    model_id, device_map="cuda:0", torch_dtype=torch.float16
)

# Example with multiple images in a single message
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg",
            },
            {
                "type": "image",
                "url": "https://thumbs.dreamstime.com/b/golden-gate-bridge-san-francisco-purple-flowers-california-echium-candicans-36805947.jpg",
            },
            {
                "type": "text",
                "text": "These images depict two different landmarks. Can you identify them?",
            },
        ],
    },
]

inputs = processor.apply_chat_template(
    messages, padding=True, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt"
).to(model.device)

gen_tokens = model.generate(
    **inputs, 
    max_new_tokens=300, 
    do_sample=True, 
    temperature=0.3,
)

gen_text = processor.tokenizer.decode(gen_tokens[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(gen_text)