Workflow de création de publicité UGC — Du script à la vidéo
Créateur complet de publicités UGC qui transforme une photo du sujet, une photo du produit et un script facultatif en une première image prête à l’emploi, puis en une vidéo verticale de 8 s avec voix et mouvements naturels de caméra à main levée.
Aperçu du workflow
Fonctionnement du template Workflow de création de publicité UGC — Du script à la vidéo
Subject
Product
Optionnal - Video Script
I’ve been wearing AI-Flow Eau de Parfum all week — it’s soft, a little sexy, and people keep asking what it is. Honestly, it feels like my new signature scent.
Video Script Prompt
To build you prompt, please check The ultimate prompting guide for Veo 3.1 made by google, and use it accordingly. Based on the image and the following script : I’ve been wearing AI-Flow Eau de Parfum all week — it’s soft, a little sexy, and people keep ask...
GPT
Vertical smartphone selfie, cozy sunlit living room. The woman sits on a couch, smiling warmly at the lens, casual white ribbed tank and light denim, subtle gold hoops, natural makeup. She presents the perfume bottle close to the camera with the cap on, lab...
Generate Image
Prompting Guide for Veo 3.1
Ultimate prompting guide for Veo 3.1 | Google Cloud Blog[Jump to Content](./#content)[Cloud](https://cloud.google.com/ "Google Cloud")[Blog](https://cloud.google.com/blog/ "Google Cloud Blog")[Contact sales](https://cloud.google.com/contact/) [Get started f...
GPT
[00:00-00:02] Selfie, handheld close-up with slight natural sway; shallow depth of field. A young woman in a white tank top smiles at camera in a bright, cozy living room with plants and shelves softly blurred. She holds a pink glass bottle labeled “AI-Flow...
Animate Image
À propos de ce template
Create authentic, high-performing UGC ads in minutes. This workflow takes a subject image and a product image, generates a realistic first-frame promo shot, and optionally animates it into a short, portrait video complete with dialogue, ambient sound, and subtle camera movement.
How it works
Upload a subject image and a product image. The system composes a clean, product-forward UGC prompt and renders a photoreal vertical first frame.
(Optional) Paste a short script. The workflow builds a timestamped animation prompt with dialogue, sound effects, ambient audio, and helpful negative prompts, then animates the still into an 8s 1080p portrait video.
Key capabilities
Image-to-image prompting that preserves the subject and product while styling for authentic UGC.
9 — 16 vertical ad assets optimized for TikTok, Instagram Reels, YouTube Shorts, and Snapchat.
Voice acting and synchronized audio driven by your script lines.
Timestamp prompting for precise beats — actions, camera notes, SFX, and pacing.
Optional reference images to guide look and consistency across variations.
Adjustable quality/speed modes and transparent cost hints within nodes.
Clean outputs — first-frame image URL and MP4 video, ready for media testing.
Best practices for strong results
Use high-resolution, well-lit subject and product images; keep labels facing camera.
Keep the first frame simple — no overlays or heavy filters; emphasize product clarity.
Write a concise 1–2 sentence script to guide tone, emotion, and callout moments.
Lean on negative prompts to avoid clutter, logos, or text artifacts in-frame.
Comment utiliser ce template
Étape 1 : Upload the subject image
This node is where you upload the image of the person who will appear in the ad. Choose a clear, well-lit image to help the model generate a realistic first-frame.
Étape 2 : Upload the product image
This node is where you upload the product image that will be featured in the ad. Make sure to use a high-quality image with the product label clearly visible to ensure the best results.
Étape 3 : Script Input (Optional)
This node allows you to input a short script (one to two sentences) that will guide the video’s dialogue and timing. If you don't provide a script, the video will be generated without specific dialogue cues.
I’ve been wearing AI-Flow Eau de Parfum all week — it’s soft, a little sexy, and people keep asking what it is. Honestly, it feels like my new signature scent.
Étape 4 : Fetching Veo 3.1 Prompting Guide for Context purpose
Here, we are fetching the Veo 3.1 Prompting Guide to provide context for the LLM. The guide helps the model understand how to generate effective video prompts based on user scripts.
The output is the content fetched from https://cloud.google.com/blog/products/ai-machine-learning/ultimate-prompting-guide-for-veo-3-1?hl=en, that we will not display here for brevity.
Étape 5 : Run the Flow
Once you run the flow, the system will process the inputs through the defined nodes, ultimately producing a first-frame image and an 8-second vertical video based on your provided subject and product images, along with any script you may have included. Feel free to customize the nodes further or adjust parameters as needed to better fit your specific use case or creative vision.
À qui s’adresse ce template ?
Idéal pour les professionnels et les créateurs qui souhaitent simplifier leur workflow
DTC and ecommerce marketers
Quickly produce product-forward UGC creatives for storefronts, paid social, and landing page tests without scheduling live shoots.
Performance marketers and UA managers
Generate vertical hooks, first frames, and 6–10s variations to accelerate creative testing across TikTok, Reels, and Shorts.
Content creators and social media managers
Turn simple selfies and product shots into on-brand UGC posts and promos with realistic movement and voice lines.
Creative strategists and UGC studios
Prototype ad concepts, iterate scripts, and maintain consistent style across campaigns using reference images and timestamp prompts.
Founders and small businesses
Launch credible UGC ads without a large budget; start from existing product photos and a brief script.
Prêt à construire ?
Commencez à utiliser ce template
Ouvrez-le directement dans AI-Flow et commencez à créer en quelques minutes
Vous aimerez peut-être aussi
Explorez d’autres templates puissants pour enrichir votre workflow IA
Génération vidéo avec Seedance 1.5 Pro
Générez des vidéos de qualité cinéma à partir de texte ou d’images, avec un audio natif parfaitement synchronisé, une synchronisation labiale précise, des mouvements de caméra cinématographiques et une forte cohérence des personnages.
Génération vidéo avec Kling V2.6
Kling V2.6 est un générateur vidéo IA professionnel qui transforme du texte ou une image en clips cinématographiques 1080p aux mouvements fluides, avec audio natif synchronisé : dialogues, ambiance et effets.
Générer des animations réalistes de synchronisation labiale à partir d’un audio
Générez des animations réalistes de synchronisation labiale à partir de n’importe quelle piste audio. PixVerse Lipsync aligne naturellement les mouvements de la bouche, le rythme de la parole et les expressions.
Génération vidéo avec Kling V2.5 Turbo Pro
Kling 2.5 Turbo Pro permet de créer des vidéos de niveau professionnel à partir de texte ou d’images, avec des mouvements fluides, une profondeur cinématographique et un excellent respect du prompt.
Sora 2
Latest version of Sora, with higher-fidelity video, context-aware audio, reference image support
Génération vidéo avec Veo 3.1
Nouvelle version améliorée de Veo 3, avec une vidéo plus fidèle, un audio sensible au contexte et la prise en charge d’une image de référence et de la dernière image.
Questions fréquentes
What does this workflow produce?
A realistic UGC first-frame image from your subject and product photos, plus an optional 8-second vertical video with dialogue, SFX, and handheld motion. Both are designed to be ad-ready.
What inputs do I need?
One subject image (the person) and one product image. Optionally, provide a short script (one to two sentences) to drive the video’s dialogue and timing.
Can I use it for image-only ads?
Yes. You can stop after generating the first-frame image if you don’t need video. The video branch is optional.
How does the script influence the video?
Your script is converted into a timestamped animation prompt with dialogue, camera notes, and audio cues. The model then animates the first frame to match the lines and timing.
Does it include voice acting and sound?
Yes. The video branch generates synchronized voice and ambient audio based on the dialogue and SFX cues in the prompt.
Which formats and specs are supported?
The workflow targets 9:16 vertical video at 1080p for approximately 8 seconds and produces a high-quality first-frame image suited to mobile placements. You can adapt the workflow for 16:9 or square formats as needed.
Can I guide the style or keep characters consistent?
Yes. Use your subject and product images as references, and optionally add extra reference images to guide style, background, or brand consistency.
How do I get better results?
Use clear, high-res photos with good lighting; ensure the product label faces the camera; keep the script concise; include negative prompts to avoid text, heavy filters, or extraneous objects.
What about cost and speed?
You can toggle quality/speed modes. The interface shows indicative pricing per image or per video second so you can choose between faster previews and higher-quality renders.
Do I need permission to use the input images?
Yes. Only upload images you have rights to use. You own the rights to your outputs per the platform’s terms, but remain responsible for input content and product claims.
Qu’est-ce qu’AI-FLOW et comment peut-il m’aider ?
AI-FLOW est une plateforme d’IA tout-en-un qui vous permet de créer, d’intégrer et d’automatiser des workflows alimentés par l’IA grâce à une interface intuitive en glisser-déposer. Débutant ou expert, vous pouvez combiner plusieurs modèles d’IA pour créer des solutions innovantes sans écrire de code.
Un essai gratuit est-il disponible ?
Oui, AI-FLOW propose un essai gratuit pour commencer. Vous pouvez ensuite acheter des crédits selon vos besoins, sans abonnement ni engagement à long terme.
Puis-je intégrer mes clés API OpenAI, Replicate et d’autres fournisseurs dans la version Cloud d’AI-FLOW ?
Oui, vous pouvez facilement intégrer vos propres clés API à AI-FLOW. Les nœuds associés utiliseront alors votre clé, ce qui réduit considérablement votre consommation de crédits sur la plateforme.