Deniz
Workflows by Deniz
Create AI-generated UGC marketing videos with Telegram & GPT-4
## 📌 How to Set Up the AI UGC Video Automation System This system uses Telegram + N8N (no-code automation) + AI models to generate user-generated content (UGC) videos automatically. ## 🔹 Overview ## Input: Send a photo of the product + character via Telegram bot. ## Process: N8N workflow handles: 1. Image analysis 2. Prompt generation 3. Image creation 4. Video clip generation 5. Combining clips into a final UGC ad Output: Video sent back to Telegram (or other destination like Google Drive/Dropbox). ## 🔹 System Workflow - ## Input Section ## Telegram Setup: 1. Create a Telegram bot and get its Bot ID. 2. Connect the bot to N8N Telegram Trigger node. 3. Bot listens for messages (photos + instructions). 4. Send Input 5. Upload one compressed image with : - Product - Character (optional) Example: “Create a UGC video with Gandalf promoting The Hobbit book. 20 seconds long.” Image Handling . N8N retrieves the image from Telegram (via file path). . OpenAI agent analyzes the image: . Extracts product details (brand, color, description). . Extracts character details (name, outfit, style). - ## Confirm Input: . System replies on Telegram: “Got it. I’m now creating your video.” ## Step 1: Create Image 1. AI Agent (Image Prompt) 2. Generates a natural, UGC-style prompt (realistic iPhone photo look). 3. Uses OpenAI GPT to structure prompt and aspect ratio (2:3 or 3:2). 4. Image Generation 5. Sends prompt + aspect ratio to Key.AI → 4.0 Image Model. 6. Waits until image is generated. Example: Gandalf holding The Hobbit book. ## Step 2: Create Video Clips 1. AI Agent (Video Prompt) 2. Creates video script and scenes (dialogue + setting). 3. Calculates how many clips needed (e.g. 20s request → 3 x 8s clips). 4. Ensures UGC style (casual, amateur look). 5. Clip Generation 6. Sends prompts to Key.AI V3 model (Fast or Quality). 7. Input: Prompt + image + aspect ratio. 8. Output: Multiple short clips (8s each). 9. Wait for Processing 10. Clips take a few minutes to generate. 11. Retrieve video URLs from Key.AI. ## Step 3: Combine Video 1. Aggregate Clips 2.Collect all video URLs (from multiple clips). 3. Merge with FFmpeg 4. Send videos to File.AI → FFmpeg Merge Service. 5. Stitches clips into one continuous video. 6. Final Output 7. Final merged video returned as a download URL. 8. N8N sends the video back to your Telegram chat (or connected storage). ## 🔹 Customization Options ## Models: V3 Fast (~$0.40/clip, cheaper, good enough). V3 Quality (~$2/clip, slightly higher quality). Video Length: AI automatically adjusts number of clips. ## Outputs: Telegram (default) Can be extended to Google Drive, Dropbox, etc. ## 🔹 Cost Image generation: a few cents. Video clips: ~$0.40 each with V3 Fast. Clip merging: < $0.01. Much cheaper than manual UGC production.
Narrative chaining: AI-generated video scene extensions with Veo3
## Structured Setup Guide: Narrative Chaining with N8N + AI ## 1. Input Setup Use a Google Sheet as the control panel. Fields required: Video URL (starting clip, ends with .mp4) Number of clips to extend (e.g., 2 extra scenes) Aspect ratio (horizontal, vertical, etc.) Model (V3 or V3 Fast) Narrative theme (guidance for story flow) Special requests (scene-by-scene instructions) Status column (e.g., "For Production", "Done") 👉 Example scene inputs: Scene 1: Naruto walks out with ramen is his hands Scene 2: Joker joins with chips ## 2. Workflow in N8N Step 1: Fetch Input Get rows in sheet → fetch the next row where status = For Production. Clear sheet 2 → reset the sheet that stores generated scenes. Edit fields (Initial Values): Video URL = starting clip Step = 1 Complete = total number of scenes requested Step 2: Looping Logic Looper Node: Runs until step = complete. Carries over current video URL → feeds into next generation. Step 3: Analyze Current Clip Send video URL to File.AI Video Understanding API. Request: Describe last frame + audio + scene details. Output: Detailed video analysis text. Step 4: Generate Prompt AI Agent creates the next scene prompt using: Context from video analysis Narrative theme (from sheet) Scene instructions (from sheet) Aspect ratio, model preference, etc. 👉 Output = video prompt for next scene Step 5: Extract Last Frame Call File.AI Extract Frame API. Parameters: Input video URL Frame = last Output = JPG image (last frame of current clip). Step 6: Generate New Scene Use Key.AI (V3 Fast) for economical video generation. POST request includes: Prompt (from AI Agent) Aspect ratio + model Image URL (last frame) → ensures seamless chaining Wait for generation to complete. 👉 Output = New clip URL (MP4) Step 7: Store & Increment Log new clip URL into Sheet 2. Increment Step by +1. Replace Video URL with the new clip. Loop back if Step < Complete. ## 3. Output Section Once all clips are generated: Gather all scene URLs from Sheet 2. Use File.AI Merge Videos API to stitch clips together: Original clip + all generated scenes. Save final MP4 output. Update Sheet 1 row with: Final video URL Status = Done ## 4. Costs Video analysis: ~$0.015 per 8s clip Frame extraction: ~0.002¢ (almost free) Clip merging: negligible (via ffmpeg backend) V3 Fast video generation (Key.AI): ~$0.30 per 8s clip
Automate lead generation with Apollo, AI parsing, and timed email follow-ups
## Good to know: - The workflow runs every hour with a randomized delay of 5–20 minutes to help distribute load. - It records the exact date and time a lead is emailed so you can track outreach. - Follow-ups are automatically scheduled two days after the initial email. ## How it works: 1. After apify completes, the JSON data is retrieved and inserted into the proper JSON node (only the JSON is removed — nothing else). 2. The agent then runs on its own, parsing the data and pushing it to Google Sheets. 3. When a lead is emailed, the system tags it with the date and time for tracking. 4. Two days later the workflow automatically triggers a follow-up, again on an hourly schedule with the same time delay. ## How to use: 1. Start by connecting your apify account to retrieve data. 2. Place the returned JSON into the designated JSON node. 3. Configure your Google Sheet where the data will be stored. 4. Adjust the time delay window or follow-up period if needed. 5. Insert your email credentials and the message. ## Requirements: - Apify account with active leads/data. - Google Sheet for storing and managing parsed lead information. - n8n credentials configured for your accounts. - email credentials Customising this workflow: You can easily extend this template to include other CRMs, different time delays, or additional notification steps. For example, push new leads to Slack, send SMS notifications, or trigger downstream analytics dashboards automatically.