Hi everyone! Does anyone have a working JSON example for the Google Gemini / Veo 3 API that successfully uses an input image in an image-to-video request? I’m specifically looking for the correct JSON structure required by the **official Veo 3 API**, not any third-party tools, wrappers, or integrations. I’ve tried multiple formats and examples I found online, but none of them actually used the image I sent in the request — the generated video always ignored my input image. If you have a working request example or an official reference, I’d really appreciate it!

can somebody help me with this? I am making an workflow for automatic invoice parsing. But this node takes ALL the data and put's it into 1 sentence. I want to see seperate things in my schema. See screenshots. While i want something like this: see second screenshot. The way to fix this is the button: " Output content as JSON" but i dont see this button: I only see simplify output. Is there an update or something or maybe I can add something with the options below? Please let me know!

I want genuine guidance from people who have actually built agencies or automation businesses. No hype replies please. I want to think clearly and make the right decisions. I started my automation journey in June 2025. I learned chatbots, workflows, and voice agents. I created content, tried outreach on LinkedIn, Facebook, and WhatsApp, and built lead magnets. But even after months of effort, I still don’t have a single proper client. I’m at a stage where I want to continue business, but I don’t want to keep repeating mistakes. I have a few serious questions, and I’d truly appreciate honest answers from people who’ve been through this: 1. Is it actually realistic to grow an automation agency today without already having a brand, money, or network? Or is most internet advice oversimplified? 2. Does being too broad really kill your business? How important is choosing ONE niche, and how do you know when you’ve picked the right one? 3. About real estate: I’ve heard most real estate businesses only care about lead generation and don’t value automation much. Is that true? Do they really not care about follow-up automation or workflow systems? 4. If lead generation sells easier, does it make more sense to start with lead gen first instead of automation? 5. Is it smarter to build long-term automation positioning even if it’s slower, or should someone in my situation focus on something that brings faster money first? 6. For people who were stuck for months or years with no clients and finally broke through – what actually changed for you? Niche, offer, positioning, or mindset? 7. If you were in my position right now, what would be your next 3 practical steps? I genuinely want clarity, not motivational keep going bro replies. I’m ready to work, but I want to move in the right direction with a realistic strategy. If you faced similar struggles and came out of it, I’d really value your perspective.

Hi everyone! I have a task to build a workflow for mass processing of product images (scale — hundreds of thousands of photos).The goal is to automatically cut out individual infographic elements (icons, the main product, zoom-in areas) and bring them to “premium” quality (studio lighting, high sharpness). Problem with GPT Image 1.5 When trying to directly cut out an object using GPT Image 1.5, the model starts to hallucinate. It redraws small details: Faces on icons change LED diode grids get distorted Fabric textures are altered As a result, the output image is no longer the same product as in the original photo. Either the model changes the appearance of the product, or the visual details become inaccurate. Are there any ways to implement this differently, or alternative approaches/models that can solve this task without such distortions?

You guys are the ai wizards of Skool. I am trying out ai image generators and don't want to use too much time on trying them all out. I need speed and precision. For a newbie to ai, using it for their Skool community, which model would you suggest?