mirror of
https://github.com/Comfy-Org/ComfyUI.git
synced 2026-08-05 10:00:28 +08:00
2 lines
7.1 KiB
JSON
2 lines
7.1 KiB
JSON
|
{"revision": 0, "last_node_id": 233, "last_link_id": 0, "nodes": [{"id": 233, "type": "dcf32045-0ee4-4efc-9aca-9f26f3a157be", "pos": [0, 1140], "size": [400, 260], "flags": {}, "order": 7, "mode": 0, "inputs": [{"name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": null}, {"name": "model", "type": "COMBO", "widget": {"name": "model"}, "link": null}, {"name": "video", "type": "VIDEO", "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": []}], "title": "Video Captioning(Gemini)", "properties": {"proxyWidgets": [["-1", "prompt"], ["-1", "model"], ["1", "seed"]], "cnr_id": "comfy-core", "ver": "0.13.0"}, "widgets_values": ["Describe this video", "gemini-2.5-pro"]}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "dcf32045-0ee4-4efc-9aca-9f26f3a157be", "version": 1, "state": {"lastGroupId": 1, "lastNodeId": 16, "lastLinkId": 17, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Video Captioning(Gemini)", "inputNode": {"id": -10, "bounding": [-6870, 2530, 120, 100]}, "outputNode": {"id": -20, "bounding": [-6240, 2530, 120, 60]}, "inputs": [{"id": "d8cbd7eb-636a-4d7b-8ff6-b22f1755e26c", "name": "prompt", "type": "STRING", "linkIds": [15], "pos": [-6770, 2550]}, {"id": "b034e26a-d114-4604-aec2-32783e86aa6b", "name": "model", "type": "COMBO", "linkIds": [16], "pos": [-6770, 2570]}, {"id": "f7363f60-a106-4e06-90af-df5f53355b98", "name": "video", "type": "VIDEO", "linkIds": [17], "pos": [-6770, 2590]}], "outputs": [{"id": "e12c6e80-5210-4328-a581-bc8924c53070", "name": "STRING", "type": "STRING", "linkIds": [6], "localized_name": "STRING", "pos": [-6220, 2550]}], "widgets": [], "nodes": [{"id": 1, "type": "GeminiNode", "pos": [-6690, 2360], "size": [390, 430], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "shape": 7, "type": "IMAGE", "link": null}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": null}, {"localized_name": "video", "name": "video", "shape": 7, "type": "VIDEO", "link": 17}, {"localized_name": "files", "name": "files", "shape": 7, "type": "GEMINI_INPUT_FILES", "link": null}, {"localized_name": "prompt", "name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": 15}, {"localized_name": "model", "name": "model", "type": "COMBO", "widget": {"name": "model"}, "link": 16}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "system_prompt", "name": "system_prompt", "shape": 7, "type": "STRING", "widget": {"name": "system_prompt"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": [6]}], "properties": {"cnr_id": "comfy-core", "ver": "0.5.1", "Node name for S&R": "GeminiNode"}, "widgets_values": ["Describe this video", "gemini-2.5-pro", 511865409297955, "randomize", "- Role: AI Video Analysis and Description Specialist\n- Background: The user requires a prompt that enables AI to analyze videos (including frame sequences, dynamic movements, audio-visual elements) and generate detailed, structured descriptions. These descriptions must be directly usable as video generation prompts to create similar videos, serving core tasks such as video content creation, creative inspiration extraction, and artistic style exploration.\n- Profile: As an AI Video Analysis and Description Specialist, you possess expertise in computer vision, video temporal sequence processing, motion analysis, and multi-modal natural language generation. You excel at interpreting dynamic visual data (frame-by-frame features + continuous motion) and translating it into precise descriptive text that fully guides the creation of new videos with matching style, rhythm, and content.\n- Skills: Proficiency in video frame feature extraction, motion trajectory recognition, temporal rhythm analysis, scene/shot segmentation, color grading detection, camera movement identification (pan/tilt/zoom/dolly), audio-visual element correlation analysis, and descriptive la
|