I struggled with figuring out how to integrate Replicate's AI models into n8n for image and video generation, so I made this simple guide to help you get started. If you want to generate creative AI images or videos through automation without hassle, this post is for you. What you'll learn: • Set up Replicate API credentials correctly in n8n • Create image generation workflows using Imagen and SeeDream models • Handle asynchronous tasks with waiting and status checking nodes • Generate AI videos using Replicate's Kling model, including start image usage • Combine workflows into one AI agent that can generate and edit images on demand\ If you want help adapting these workflows to your specific projects or have questions, let me know in the comments!

I’m testing a new format where I show exactly what’s possible for business with no-code tools and AI. Today: a case from my current project - massive analysis and creation of video content. Types of businesses with this task: - Marketing agencies – produce lots of content for many clients - E-commerce – stores that create content to promote products - Creators – large players with systematic content across multiple platforms Core process: Find a viral reference ⬇️ Analyze it ⬇️ Copy the structure ⬇️ Create the video ⬇️ Analyze the results ⬇️ Repeat if it worked Tasks that can be automated (with guides): - Finding viral references – manually curated database + scraping via Apify - Analyzing structure of viral videos – video analysis with Gemini - Creating the video – audio/voice generation with 11Labs, image generation with OpenAI/Midjourney/Flux, video generation with Veo3/Runway/Kling - Analyzing metrics of your own content – scraping via Apify - Comparing your video vs. the reference – video analysis with Gemini Project characteristics: - Budget: $5,000–12,000 depending on scope - Ongoing costs: depends on volume of videos - - Scraping: $5–10 per 1,000 videos - - Video creation: $2–10 per video - - Video analysis: $5 per 100 videos - Timeline: 1 week per every 2 steps + 1 week for project setup How do you like this format? Which business task should I break down next? __ We have ready-to-use guides for each of processes in our community https://www.skool.com/5minai-pro

Hello everyone! A few months ago you voted in a poll for more content about content generation. Is it still relevant for you? Please tell me in comments. So, I'm preparing a guide to content generation with consistent characters based on new OpenAI model. System will be based on Airtable with ability to control intermediate steps with stories, images, video and sound. ➡️ Curious to know the opinion of creators in this niche - What do you think? Do you have any particular obstacles with content creation systems?

Hey everyone! Just dropped a new tool that I’ve been using for generating high-quality product images on autopilot — and it’s live now inside the paid community. This setup combines OpenAI, Airtable, and n8n to create a fully automated image generation workflow. With this tool, you can: - Generate AI images from custom prompts - Use reference photos to recreate visuals in your own style - Combine your product + inspiration images to generate branded assets - Control image size, quality, quantity, and format - Store and manage all results inside Airtable (linked to products/prompts) Example Use Cases - E-commerce: Bulk-generate product visuals for Amazon, Etsy, or Shopify - Marketing Teams: Quickly test variations of ad creatives or product mockups - Template-Based Work: Use prompt libraries for consistent visual themes across multiple products ➡️ All workflows and templates to copy this tool are in our paid community - 5minAI PRO

Yesterday I watched a video from AI Engineer Summit (if you haven't seen it, there are 3 dozen top AI talks). At one of the presentations, the speaker showed an interesting approach to working with AI agents. The agent gets access to the necessary tools (database, API services, etc.) and processes a user request as input. Using these tools, the agent builds an interface in real time that matches the specific task. An example was shown on the screen - a simple email interface. The user interacts with this interface - for example, clicks on an email and the agent receives data about this action. It then analyzes what the user is likely to want to see next and updates the interface, tailoring it to the next step - in this case displaying the contents of the selected email. Thus, with access to the data and the context of the interaction, the agent is able to shape interfaces on the fly to the user's current need. Of course, this approach has limitations: everything works quite slowly now, the interfaces are simple, and the result can change from request to request. But if we introduce a system of rules and speed up the AI's reaction, then in the future we can get really adaptive interfaces that will automatically adjust to the user's tasks without unnecessary tinsel. Watch the presentation here