This ComfyUI workflow lets you edit a short video by simply describing the change you want. LoadVideo ingests your clip (the template includes input/hooded_wanderer_planet_bridge.mp4 as a ready-to-run test), and GeminiVideoOmniV2 sends both the video and your plain‑language instruction to Gemini Omni 1.1 Flash. The model applies targeted edits—like swapping backgrounds, restyling a scene, or adding/removing elements—while leaving everything else untouched. For maximum fidelity, include a line such as “Keep everything else the same.” Simple, direct prompts tend to produce the most consistent results.
On output, SaveVideo writes the edited clip to disk with the native audio preserved. You can choose 16:9 or 9:16 and render at 1080p or 4K, making it suitable for landscape or vertical content. A MarkdownNote in the graph provides quick tips. The recommended input duration is 10 seconds or less to ensure responsive processing and stable edits. This setup is ideal for rapid remixes and iterative refinement without regenerating entire scenes from scratch.
API
Utiliser ce workflow depuis le code
Chaque workflow Comfy est un graphe JSON. Le contenu ci-dessous est ce workflow, exactement comme ComfyUI l’exécute — récupérez-le depuis l’URL, gardez-le dans le contrôle de version, ou chargez-le dans ComfyUI et exécutez-le nœud par nœud.
Exécutez-le depuis TypeScript ou Python avec le Comfy SDK. Le même code cible Comfy Cloud ou un ComfyUI auto-hébergé — seule l’URL de base change.
// Install (beta)
npm i @comfyorg/sdk
// Run this workflow (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
const wf = await client.workflows.fromFile("workflow_api.json");
const job = await client.run(wf);
await job.getOutputs("<output-node-id>")[0].toFile("output.png");Le SDK prend un workflow au format API : ouvrez ce workflow dans ComfyUI et utilisez Fichier → Exporter le workflow (API).
L’accès à l’API Comfy Cloud nécessite un forfait avec clé API.
