demos/demo_parse_task.json

[
    {
        "role": "user",
        "content": "Give you some pictures e1.jpg, e2.png, e3.jpg, help me count the number of sheep?"
    },
    {
        "role": "assistant",
        "content": [
            {
                "task": "image-to-text",
                "id": 0,
                "dep": [-1],
                "args": {
                    "image": "e1.jpg"
                }
            },
            {
                "task": "object-detection",
                "id": 1,
                "dep": [-1],
                "args": {
                    "image": "e1.jpg"
                }
            },
            {
                "task": "visual-question-answering",
                "id": 2,
                "dep": [1],
                "args": {
                    "image": "<GENERATED>-1",
                    "text": "How many sheep in the picture"
                }
            },
            {
                "task": "image-to-text",
                "id": 3,
                "dep": [-1],
                "args": {
                    "image": "e2.png"
                }
            },
            {
                "task": "object-detection",
                "id": 4,
                "dep": [-1],
                "args": {
                    "image": "e2.png"
                }
            },
            {
                "task": "visual-question-answering",
                "id": 5,
                "dep": [4],
                "args": {
                    "image": "<GENERATED>-4",
                    "text": "How many sheep in the picture"
                }
            },
            {
                "task": "image-to-text",
                "id": 6,
                "dep": [-1],
                "args": {
                    "image": "e3.jpg"
                }
            },
            {
                "task": "object-detection",
                "id": 7,
                "dep": [-1],
                "args": {
                    "image": "e3.jpg"
                }
            },
            {
                "task": "visual-question-answering",
                "id": 8,
                "dep": [7],
                "args": {
                    "image": "<GENERATED>-7",
                    "text": "How many sheep in the picture"
                }
            }
        ]
    },


    {
        "role": "user",
        "content": "Look at /e.jpg, can you tell me how many objects in the picture? Give me a picture and video similar to this one."
    },
    {
        "role": "assistant",
        "content": [
            {
                "task": "image-to-text",
                "id": 0,
                "dep": [-1],
                "args": {
                    "image": "/e.jpg"
                }
            },
            {
                "task": "object-detection",
                "id": 1,
                "dep": [-1],
                "args": {
                    "image": "/e.jpg"
                }
            },
            {
                "task": "visual-question-answering",
                "id": 2,
                "dep": [1],
                "args": {
                    "image": "<GENERATED>-1",
                    "text": "how many objects in the picture?"
                }
            },
            {
                "task": "text-to-image",
                "id": 3,
                "dep": [0],
                "args": {
                    "text": "<GENERATED-0>"
                }
            },
            {
                "task": "image-to-image",
                "id": 4,
                "dep": [-1],
                "args": {
                    "image": "/e.jpg"
                }
            },
            {
                "task": "text-to-video",
                "id": 5,
                "dep": [0],
                "args": {
                    "text": "<GENERATED-0>"
                }
            }
        ]
    },

    {
        "role": "user",
        "content": "given a document /images/e.jpeg, answer me what is the student amount? And describe the image with your voice"
    },
    {
        "role": "assistant",
        "content": [
            {
                "task": "document-question-answering",
                "id": 0,
                "dep": [-1],
                "args": {
                    "image": "/images/e.jpeg",
                    "text": "what is the student amount?"
                }
            },
            {
                "task": "visual-question-answering",
                "id": 1,
                "dep": [-1],
                "args": {
                    "image": "/images/e.jpeg",
                    "text": "what is the student amount?"
                }
            },
            {
                "task": "image-to-text",
                "id": 2,
                "dep": [-1],
                "args": {
                    "image": "/images/e.jpeg"
                }
            },
            {
                "task": "text-to-speech",
                "id": 3,
                "dep": [2],
                "args": {
                    "text": "<GENERATED>-2"
                }
            }
        ]
    },


    {
        "role": "user",
        "content": "Given an image /example.jpg, first generate a pose image, then based on the pose generate a new image where a girl is reading a book"
    },
    {
        "role": "assistant",
        "content": [
            {
                "task": "openpose-control",
                "id": 0,
                "dep": [-1],
                "args": {
                    "image": "/example.jpg"
                }
            },
            {
                "task": "openpose-text-to-image",
                "id": 1,
                "dep": [0],
                "args": {
                    "text": "a girl is reading a book",
                    "image": "<GENERATED>-0"
                }
            }
        ]
    },


    {
        "role": "user",
        "content": "please show me a video and an image of (based on the text) 'a boy is running' and dub it"
    },
    {
        "role": "assistant",
        "content": [
            {
                "task": "text-to-video",
                "id": 0,
                "dep": [-1],
                "args": {
                    "text": "a boy is running"
                }
            },
            {
                "task": "text-to-speech",
                "id": 1,
                "dep": [-1],
                "args": {
                    "text": "a boy is running"
                }
            },
            {
                "task": "text-to-image",
                "id": 2,
                "dep": [-1],
                "args": {
                    "text": "a boy is running"
                }
            }
        ]
    },

    {
        "role": "user",
        "content": "please show me a joke and an image of cat"
    },
    {
        "role": "assistant",
        "content": [
            {
                "task": "conversational",
                "id": 0,
                "dep": [-1],
                "args": {
                    "text": "please show me a joke of cat"
                }
            },
            {
                "task": "text-to-image",
                "id": 1,
                "dep": [-1],
                "args": {
                    "text": "a photo of cat"
                }
            }
        ]
    },


    {
        "role": "user",
        "content": "give me a picture about a cut dog, then describe the image to me and tell a story about it"
    },
    {
        "role": "assistant",
        "content": [
            {
                "task": "text-to-image",
                "id": 0,
                "dep": [-1],
                "args": {
                    "text": "a picture of a cute dog" 
                }
            },
            {
                "task": "image-to-text",
                "id": 1,
                "dep": [0],
                "args": {
                    "image": "<GENERATED>-0"
                }
            },
            {
                "task": "text-generation",
                "id": 2,
                "dep": [1],
                "args": {
                    "text": "<GENERATED>-1"
                }
            },
            {
                "task": "text-to-speech",
                "id": 3,
                "dep": [2],
                "args": {
                    "text": "<GENERATED>-2"
                }
            }
        ]
    },


    {
        "role": "user",
        "content": "give you a picture /example.jpg, what's in it and tell me a joke about it"
    },
    {
        "role": "assistant",
        "content": [
            {
                "task": "image-to-text",
                "id": 0,
                "dep": [-1],
                "args": {
                    "image": "/example.jpg"
                }
            },
            {
                "task": "object-detection",
                "id": 1,
                "dep": [-1],
                "args": {
                    "image": "/example.jpg"
                }
            },
            {
                "task": "conversational",
                "id": 2,
                "dep": [0],
                "args": {
                    "text": "<GENERATED>-0"
                }
            },
            {
                "task": "text-to-speech",
                "id": 3,
                "dep": [2],
                "args": {
                    "text": "<GENERATED>-1"
                }
            }
        ]
    }
]