InternVL3-8B-hf

>>> from transformers import pipeline

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {
...                 "type": "image",
...                 "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
...             },
...             {"type": "text", "text": "Describe this image."},
...         ],
...     },
... ]

>>> pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-8B-hf")
>>> outputs = pipe(text=messages, max_new_tokens=50, return_full_text=False)
>>> outputs[0]["generated_text"]
'The image showcases a vibrant scene of nature, featuring several flowers and a bee. \n\n1. **Foreground Flowers**: \n   - The primary focus is on a large, pink cosmos flower with a prominent yellow center. The petals are soft and slightly r'

>>> from transformers import pipeline

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {
...                 "type": "image",
...                 "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
...             },
...             {"type": "text", "text": "Describe this image."},
...         ],
...     },
... ]

>>> pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-8B-hf")
>>> outputs = pipe(text=messages, max_new_tokens=50, return_full_text=False)
>>> outputs[0]["generated_text"]
'The image showcases a vibrant scene of nature, featuring several flowers and a bee. \n\n1. **Foreground Flowers**: \n   - The primary focus is on a large, pink cosmos flower with a prominent yellow center. The petals are soft and slightly r'

>>> from transformers import pipeline

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {
...                 "type": "image",
...                 "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
...             },
...             {"type": "text", "text": "Describe this image."},
...         ],
...     },
... ]

>>> pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-8B-hf")
>>> outputs = pipe(text=messages, max_new_tokens=50, return_full_text=False)
>>> outputs[0]["generated_text"]
'The image showcases a vibrant scene of nature, featuring several flowers and a bee. \n\n1. **Foreground Flowers**: \n   - The primary focus is on a large, pink cosmos flower with a prominent yellow center. The petals are soft and slightly r'

>>> from transformers import pipeline

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {
...                 "type": "image",
...                 "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
...             },
...             {"type": "text", "text": "Describe this image."},
...         ],
...     },
... ]

>>> pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-8B-hf")
>>> outputs = pipe(text=messages, max_new_tokens=50, return_full_text=False)
>>> outputs[0]["generated_text"]
'The image showcases a vibrant scene of nature, featuring several flowers and a bee. \n\n1. **Foreground Flowers**: \n   - The primary focus is on a large, pink cosmos flower with a prominent yellow center. The petals are soft and slightly r'

>>> from transformers import pipeline

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {
...                 "type": "image",
...                 "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
...             },
...             {"type": "text", "text": "Describe this image."},
...         ],
...     },
... ]

>>> pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-8B-hf")
>>> outputs = pipe(text=messages, max_new_tokens=50, return_full_text=False)
>>> outputs[0]["generated_text"]
'The image showcases a vibrant scene of nature, featuring several flowers and a bee. \n\n1. **Foreground Flowers**: \n   - The primary focus is on a large, pink cosmos flower with a prominent yellow center. The petals are soft and slightly r'

>>> from transformers import pipeline

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {
...                 "type": "image",
...                 "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
...             },
...             {"type": "text", "text": "Describe this image."},
...         ],
...     },
... ]

>>> pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-8B-hf")
>>> outputs = pipe(text=messages, max_new_tokens=50, return_full_text=False)
>>> outputs[0]["generated_text"]
'The image showcases a vibrant scene of nature, featuring several flowers and a bee. \n\n1. **Foreground Flowers**: \n   - The primary focus is on a large, pink cosmos flower with a prominent yellow center. The petals are soft and slightly r'

>>> from transformers import pipeline

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {
...                 "type": "image",
...                 "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
...             },
...             {"type": "text", "text": "Describe this image."},
...         ],
...     },
... ]

>>> pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-8B-hf")
>>> outputs = pipe(text=messages, max_new_tokens=50, return_full_text=False)
>>> outputs[0]["generated_text"]
'The image showcases a vibrant scene of nature, featuring several flowers and a bee. \n\n1. **Foreground Flowers**: \n   - The primary focus is on a large, pink cosmos flower with a prominent yellow center. The petals are soft and slightly r'

>>> from transformers import pipeline

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {
...                 "type": "image",
...                 "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
...             },
...             {"type": "text", "text": "Describe this image."},
...         ],
...     },
... ]

>>> pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-8B-hf")
>>> outputs = pipe(text=messages, max_new_tokens=50, return_full_text=False)
>>> outputs[0]["generated_text"]
'The image showcases a vibrant scene of nature, featuring several flowers and a bee. \n\n1. **Foreground Flowers**: \n   - The primary focus is on a large, pink cosmos flower with a prominent yellow center. The petals are soft and slightly r'

>>> from transformers import AutoProcessor, AutoModelForImageTextToText
>>> import torch

>>> torch_device = "cuda"
>>> model_checkpoint = "OpenGVLab/InternVL3-8B-hf"
>>> processor = AutoProcessor.from_pretrained(model_checkpoint)
>>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
...             {"type": "text", "text": "Please describe the image explicitly."},
...         ],
...     }
... ]

>>> inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)

>>> generate_ids = model.generate(**inputs, max_new_tokens=50)
>>> decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)

>>> decoded_output
'The image shows two cats lying on a pink blanket. The cat on the left is a tabby with a mix of brown, black, and white fur, and it appears to be sleeping with its head resting on the blanket. The cat on the'

>>> from transformers import AutoProcessor, AutoModelForImageTextToText
>>> import torch

>>> torch_device = "cuda"
>>> model_checkpoint = "OpenGVLab/InternVL3-8B-hf"
>>> processor = AutoProcessor.from_pretrained(model_checkpoint)
>>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
...             {"type": "text", "text": "Please describe the image explicitly."},
...         ],
...     }
... ]

>>> inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)

>>> generate_ids = model.generate(**inputs, max_new_tokens=50)
>>> decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)

>>> decoded_output
'The image shows two cats lying on a pink blanket. The cat on the left is a tabby with a mix of brown, black, and white fur, and it appears to be sleeping with its head resting on the blanket. The cat on the'

>>> from transformers import AutoProcessor, AutoModelForImageTextToText
>>> import torch

>>> torch_device = "cuda"
>>> model_checkpoint = "OpenGVLab/InternVL3-8B-hf"
>>> processor = AutoProcessor.from_pretrained(model_checkpoint)
>>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
...             {"type": "text", "text": "Please describe the image explicitly."},
...         ],
...     }
... ]

>>> inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)

>>> generate_ids = model.generate(**inputs, max_new_tokens=50)
>>> decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)

>>> decoded_output
'The image shows two cats lying on a pink blanket. The cat on the left is a tabby with a mix of brown, black, and white fur, and it appears to be sleeping with its head resting on the blanket. The cat on the'

>>> from transformers import AutoProcessor, AutoModelForImageTextToText
>>> import torch

>>> torch_device = "cuda"
>>> model_checkpoint = "OpenGVLab/InternVL3-8B-hf"
>>> processor = AutoProcessor.from_pretrained(model_checkpoint)
>>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
...             {"type": "text", "text": "Please describe the image explicitly."},
...         ],
...     }
... ]

>>> inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)

>>> generate_ids = model.generate(**inputs, max_new_tokens=50)
>>> decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)

>>> decoded_output
'The image shows two cats lying on a pink blanket. The cat on the left is a tabby with a mix of brown, black, and white fur, and it appears to be sleeping with its head resting on the blanket. The cat on the'

>>> from transformers import AutoProcessor, AutoModelForImageTextToText
>>> import torch

>>> torch_device = "cuda"
>>> model_checkpoint = "OpenGVLab/InternVL3-8B-hf"
>>> processor = AutoProcessor.from_pretrained(model_checkpoint)
>>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
...             {"type": "text", "text": "Please describe the image explicitly."},
...         ],
...     }
... ]

>>> inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)

>>> generate_ids = model.generate(**inputs, max_new_tokens=50)
>>> decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)

>>> decoded_output
'The image shows two cats lying on a pink blanket. The cat on the left is a tabby with a mix of brown, black, and white fur, and it appears to be sleeping with its head resting on the blanket. The cat on the'

>>> from transformers import AutoProcessor, AutoModelForImageTextToText
>>> import torch

>>> torch_device = "cuda"
>>> model_checkpoint = "OpenGVLab/InternVL3-8B-hf"
>>> processor = AutoProcessor.from_pretrained(model_checkpoint)
>>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
...             {"type": "text", "text": "Please describe the image explicitly."},
...         ],
...     }
... ]

>>> inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)

>>> generate_ids = model.generate(**inputs, max_new_tokens=50)
>>> decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)

>>> decoded_output
'The image shows two cats lying on a pink blanket. The cat on the left is a tabby with a mix of brown, black, and white fur, and it appears to be sleeping with its head resting on the blanket. The cat on the'

>>> from transformers import AutoProcessor, AutoModelForImageTextToText
>>> import torch

>>> torch_device = "cuda"
>>> model_checkpoint = "OpenGVLab/InternVL3-8B-hf"
>>> processor = AutoProcessor.from_pretrained(model_checkpoint)
>>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
...             {"type": "text", "text": "Please describe the image explicitly."},
...         ],
...     }
... ]

>>> inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)

>>> generate_ids = model.generate(**inputs, max_new_tokens=50)
>>> decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)

>>> decoded_output
'The image shows two cats lying on a pink blanket. The cat on the left is a tabby with a mix of brown, black, and white fur, and it appears to be sleeping with its head resting on the blanket. The cat on the'

>>> from transformers import AutoProcessor, AutoModelForImageTextToText
>>> import torch

>>> torch_device = "cuda"
>>> model_checkpoint = "OpenGVLab/InternVL3-8B-hf"
>>> processor = AutoProcessor.from_pretrained(model_checkpoint)
>>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)

>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
...             {"type": "text", "text": "Please describe the image explicitly."},
...         ],
...     }
... ]

>>> inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)

>>> generate_ids = model.generate(**inputs, max_new_tokens=50)
>>> decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)

>>> decoded_output
'The image shows two cats lying on a pink blanket. The cat on the left is a tabby with a mix of brown, black, and white fur, and it appears to be sleeping with its head resting on the blanket. The cat on the'