File size: 7,563 Bytes
a7438d2
 
9997f92
0910455
7dd6d04
 
a7438d2
 
 
 
 
 
 
91840f8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e26e1c
 
 
91840f8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
744140b
91840f8
 
 
 
744140b
91840f8
 
 
 
a6b28a4
91840f8
 
 
 
 
 
 
 
a7438d2
91840f8
 
 
 
 
4269cb2
a7438d2
 
 
 
5973976
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
import gradio as gr
from llm_inference_video import VideoLLMInferenceNode

title = """<h1 align="center">AI Video Prompt Generator</h1>
<p align="center">Generate creative video prompts with technical specifications</p>
<p align="center">You can use prompts with Kling, MiniMax, Hunyuan, Haiper, CogVideoX, Luma, LTX, Runway, PixVerse. </p>"""

def create_video_interface():
    llm_node = VideoLLMInferenceNode()

    with gr.Blocks(theme='bethecloud/storj_theme') as demo:
        gr.HTML(title)
        
        with gr.Tab("Video Prompt Generator"):
            with gr.Row():
                with gr.Column(scale=1):
                    input_concept = gr.Textbox(label="Core Concept/Thematic Input", lines=3)
                    style = gr.Dropdown(
                        choices=["Minimalist", "Simple", "Detailed", "Descriptive", "Dynamic", 
                                "Cinematic", "Documentary", "Animation", "Action", "Experimental"],
                        value="Simple",
                        label="Video Style"
                    )
                    custom_elements = gr.Textbox(label="Custom Technical Elements", 
                                               placeholder="e.g., Infrared hybrid, Datamosh transitions")
                    prompt_length = gr.Dropdown(
                        choices=["Short", "Medium", "Long"],
                        value="Medium",
                        label="Prompt Length"
                    ) 
                    
                with gr.Column(scale=1):
                    camera_direction = gr.Dropdown(
                        choices=[
                            "None",
                            "Zoom in", "Zoom out", "Pan left", "Pan right",
                            "Tilt up", "Tilt down", "Orbital rotation",
                            "Push in", "Pull out", "Track forward", "Track backward",
                            "Spiral in", "Spiral out", "Arc movement",
                            "Diagonal traverse", "Vertical rise", "Vertical descent"
                        ],
                        value="None",
                        label="Camera Direction"
                    )

                    camera_style = gr.Dropdown(
                        choices=[
                            "None",
                            "Steadicam flow", "Drone aerials", "Handheld urgency", "Crane elegance",
                            "Dolly precision", "VR 360", "Multi-angle rig", "Static tripod",
                            "Gimbal smoothness", "Slider motion", "Jib sweep", "POV immersion",
                            "Time-slice array", "Macro extreme", "Tilt-shift miniature",
                            "Snorricam character", "Whip pan dynamics", "Dutch angle tension",
                            "Underwater housing", "Periscope lens"
                        ],
                        value="None",
                        label="Camera Movement Style"
                    )

                    pacing = gr.Dropdown(
                        choices=[
                            "None",
                            "Slow burn", "Rhythmic pulse", "Frantic energy", "Ebb and flow",
                            "Hypnotic drift", "Time-lapse rush", "Stop-motion staccato",
                            "Gradual build", "Quick cut rhythm", "Long take meditation",
                            "Jump cut energy", "Match cut flow", "Cross-dissolve dreamscape",
                            "Parallel action", "Slow motion impact", "Ramping dynamics",
                            "Montage tempo", "Continuous flow", "Episodic breaks"
                        ],
                        value="None",
                        label="Pacing Rhythm"
                    )
                    special_effects = gr.Dropdown(
                        choices=[
                            "None",
                            "Practical effects", "CGI enhancement", "Analog glitches",
                            "Light painting", "Projection mapping", "Nanosecond exposures",
                            "Double exposure", "Smoke diffusion", "Lens flare artistry",
                            "Particle systems", "Holographic overlay", "Chromatic aberration",
                            "Digital distortion", "Wire removal", "Motion capture",
                            "Miniature integration", "Weather simulation", "Color grading",
                            "Mixed media composite", "Neural style transfer"
                        ],
                        value="None",
                        label="SFX Approach"
                    )
                    
                with gr.Column(scale=1):
                    provider = gr.Dropdown(
                        choices=["SambaNova", "Groq"],
                        value="SambaNova",
                        label="LLM Provider"
                    )
                    model = gr.Dropdown(
                        choices=[
                            "Meta-Llama-3.1-70B-Instruct",
                            "Meta-Llama-3.1-405B-Instruct",
                            "Meta-Llama-3.1-8B-Instruct"
                        ],
                        value="Meta-Llama-3.1-70B-Instruct",
                        label="Model"
                    )
                    

                    generate_btn = gr.Button("Generate Video Prompt", variant="primary")
                    output = gr.Textbox(label="Generated Prompt", lines=12, show_copy_button=True)

            def update_models(provider):
                models = {
                    "Groq": ["llama-3.3-70b-versatile"],
                    "SambaNova": [
                        "Meta-Llama-3.1-70B-Instruct",
                        "Meta-Llama-3.1-405B-Instruct",
                        "Meta-Llama-3.1-8B-Instruct"
                    ]
                }
                return gr.Dropdown(choices=models[provider], value=models[provider][0])

            provider.change(update_models, inputs=provider, outputs=model)

            generate_btn.click(
                llm_node.generate_video_prompt,
                inputs=[input_concept, style, camera_style, camera_direction, pacing, special_effects, 
                       custom_elements, provider, model, prompt_length],
                outputs=output
            )

        with gr.Tab("Visual Analysis"):
            with gr.Row():
                with gr.Column():
                    image_input = gr.Image(label="Upload Image", type="filepath")
                    image_question = gr.Textbox(
                        label="Question (optional)", 
                        placeholder="What is in this image?"
                    )

                    analyze_image_btn = gr.Button("Analyze Image")
                    image_output = gr.Textbox(label="Analysis Result", lines=5)

                with gr.Column():
                    video_input = gr.Video(label="Upload Video")
                    analyze_video_btn = gr.Button("Analyze Video")
                    video_output = gr.Textbox(label="Video Analysis", lines=10)

            analyze_image_btn.click(
                llm_node.analyze_image,
                inputs=[image_input, image_question],
                outputs=image_output
            )

            analyze_video_btn.click(
                llm_node.analyze_video,
                inputs=video_input,
                outputs=video_output
            )

    return demo

if __name__ == "__main__":
    demo = create_video_interface()
    demo.launch(share=True)