# MaxVideoAI: Turn a Product Photo into a Short Clip with Milo > Turn one product photo into a 5-second vertical clip in MaxVideoAI Studio: brief Milo, compare models, see the exact price first, and watch the real… Source: https://learn.ynteractive.com/content/maxvideoai-product-photo-to-short-clip · Updated 2026-11-09 · Free from Stepthrough (https://learn.ynteractive.com) ## Practice it step by step [Start the free practice](https://learn.ynteractive.com/modules/maxvideoai-product-photo-clip) [Take the free module: why it matters, practice and a quick check →](https://learn.ynteractive.com/courses/ai-apps-worth-knowing/56) You do every step yourself in a practice copy of MaxVideoAI. It checks your work as you go, and “Do it for me” finishes any step you get stuck on. Free, about 8 minutes, and nothing touches your real accounts. [Open full screen](https://learn.ynteractive.com/modules/maxvideoai-product-photo-clip) Free · Live now · [AI Automation for Marketing](https://learn.ynteractive.com/content/industry/marketing) · MaxVideoAI · ~8 min · 14 steps · Beginner Updated November 9, 2026. Built against the tool’s current screens and checked step by step. [How we check this lesson](https://learn.ynteractive.com/content/about#how-we-check) Small brands need short vertical clips for Instagram and their product pages, but most have one good product photo and no budget for a video shoot. MaxVideoAI is a pay-as-you-go AI video platform with many models in one place. Its Studio has an assistant, Milo, that reads your brief, picks the model, writes the [prompt](https://learn.ynteractive.com/content/glossary/prompt) and shows you the exact price before anything is generated. In this free lesson you use a practice copy built from real MaxVideoAI Studio screens: you upload a product photo, brief Milo, compare three models, get an exact quote for a 5-second, 720p vertical clip, confirm it, and watch the real clip MaxVideoAI made for 39 cents. ## At a glance | Question | Answer | | --- | --- | | What you build | One good product photo, no video budget. Give MaxVideoAI Studio the photo and a short brief, let Milo pick the model and write the prompt, and see the exact price of a 5-second vertical clip before anything is generated. | | Tools | MaxVideoAI | | Time | About 8 minutes, 14 steps in 3 parts | | Level | Beginner, no coding needed | | Cost | Free | | Ways to learn it | [Practice it step by step](https://learn.ynteractive.com/modules/maxvideoai-product-photo-clip) | ### The 3 parts, in short 1. Bring in the product photo: Add a reference, Upload from device. 2. Brief Milo: Choose Standard, Continue with Standard, Write the brief, Send it to Milo, and 1 more step. 3. Pick a model and get the quote: Compare the models, Ask for the exact quote, Jump to the answer, Open the direction, and 3 more steps. **Start here first:** [Build an n8n AI Agent That Plans Your Content Calendar](https://learn.ynteractive.com/content/n8n-ai-agent-content-calendar) (module 1 of AI Automation for Marketing) **Part of:** [AI Apps Worth Knowing](https://learn.ynteractive.com/content/paths/partner-tools-ai-apps) (step 128 of 140). Next up: [Floot: Build an Office Request Tracker from a Claude Chat](https://learn.ynteractive.com/content/floot-office-request-tracker-from-claude) **Part of:** [AI Video & Audio for Marketing](https://learn.ynteractive.com/content/paths/ai-video-audio-marketing) (step 9 of 9) ## The business case: one photo, no video budget Picture the marketing lead at Fieldnote, a made-up coffee roaster with a new cold brew in a can. The product page and Instagram both want motion, but a videographer for a 5-second product shot costs far more than the shot is worth to a small brand. With one good photo and a clear brief, an image-to-video model can make that clip for well under a dollar. The work that is left is the brief, the model choice and checking the result, and Milo helps with the first two. ## Who this is for, and what you need Marketing coordinators, small-business owners and agency staff who post product content. You need a MaxVideoAI account, a sharp product photo with a plain background, and wallet funds for the clip itself. Milo's own work runs on Milo [credits](https://learn.ynteractive.com/content/glossary/ai-credits); our account came with 500 included for the month. ## Milo credits and your wallet are two different meters Milo has three modes: Lite for everyday chat, Standard for creative work and planning, and Max for complex direction. Each request shows a live meter with a maximum it never goes over; ours used 30 credits for the first answer and 70 for the whole conversation, out of 500 included (1,000 credits = $1). The video itself is paid from your wallet, with a separate quote for every generation. With $0.00 in the wallet, the quote card says Insufficient balance and offers Add funds and Refresh balance, so nothing can be spent by accident. Once funded, the same card shows your available balance and a Create video button with the price on it, charged only when you confirm. ## What Milo quoted for one 5-second clip For one 5-second vertical clip from the photo, Milo estimated Wan 3 at 480p for $0.33, FLUX 3 Draft at 720p for $0.39 and Dreamina Seedance 2.0 Mini at 480p for $0.43, and recommended FLUX 3 Draft for the sharper resolution. The exact quote for FLUX 3 Draft, 9:16, 720p, 5 s, silent, with the photo as the start frame, was $0.39. Prices were the same on 6 and 9 November 2026; check the quote card for today's price. Milo was honest about the risk: it told the model to keep the FIELDNOTE label exactly, but said animation cannot guarantee the lettering stays pixel-exact, and that a 9:16 frame may crop the sides of the photo. ## What this saves you - A product clip for well under a dollar instead of a video shoot. - No surprises: the price shows before every generation, and nothing runs without funds and your confirmation. - Less [prompt writing](https://learn.ynteractive.com/content/prompt-writing-101-role-context-task-format): Milo turns a plain-English brief into a model prompt you can read and change. - What it does not do: it cannot promise the label text stays perfect, so check every clip before you post it. ## What the real clip looks like The last step of the lesson plays the clip MaxVideoAI generated on 9 November 2026 from the Fieldnote photo with FLUX 3 Draft: 5 seconds, 9:16, 704x1280 pixels at 24 frames per second, silent. The camera pushes in slowly, the light on the window sill shifts, condensation drops sit on the can, and the FIELDNOTE label and the small text under it stayed sharp for the whole clip. It took about a minute, and the wallet went from $10.00 to $9.61: exactly the $0.39 quoted. ## What we checked in a real account Every step was done in a real MaxVideoAI account. On 6 November 2026: the upload, the Milo modes and credits, the brief, the three-model comparison, the exact quote and the direction Milo wrote, with a $0.00 wallet, so that run stopped at Insufficient balance. On 9 November 2026, after MaxVideoAI added $10 of credits, we ran the same brief and quote again (same three prices), clicked Create video · $0.39, and got the clip that plays in the last step. ## Links - [MaxVideoAI](https://maxvideoai.com/studio): the AI video platform this lesson teaches. It has its own account and pay-as-you-go pricing. ## Try it yourself, free Reading the steps is a start. Doing them is how it sticks. The interactive module walks you through every click in a practice copy of MaxVideoAI, checks each step, and never touches your real accounts. [Start “MaxVideoAI: Turn a Product Photo into a Short Clip with Milo”](https://learn.ynteractive.com/modules/maxvideoai-product-photo-clip) ## Step by step: MaxVideoAI: Turn a Product Photo into a Short Clip with Milo All 14 steps of the interactive module, in order. In the module you watch each one, then do it yourself in a practice copy that checks your work. ### 1. Bring in the product photo 1. **Add a reference.** You run marketing at **Fieldnote**, a made-up coffee roaster that sells a cold brew in a can. This is **MaxVideoAI Studio**, where you describe what you want and its assistant, **Milo**, picks the model and writes the prompt. Start with your product photo. Click the **+** button in the prompt box. This is MaxVideoAI Studio. You describe the clip, and its assistant, Milo, picks the model and writes the prompt. Start with your product photo. 2. **Upload from device.** The **MaxVideoAI library** keeps every image, video and audio file you add. It is empty, so click **Upload from device** and pick your photo. Ours is the Fieldnote can on a sunny window sill: one product, a plain background, a sharp label. The library is empty. One product, a plain background and a sharp label work best. ### 2. Brief Milo 3. **Choose Standard.** The photo is in as **Image 1**, with an **Image 1** chip above the prompt box. Under the box, Milo has three modes and starts on **Max**. A single product clip does not need the biggest one. Click **Standard**. The photo is in, as Image 1. Milo starts on Max. A product clip does not need the biggest mode. 4. **Continue with Standard.** Milo explains its modes: **Lite** for everyday chat, **Standard** for creative work and planning, **Max** for complex direction. Milo's own work uses **Milo credits**, and the account comes with **500** included this month (1,000 credits = $1). The video itself is priced separately. Click **Continue with Standard**. Lite, Standard and Max. Milo's own work uses Milo credits, and you get five hundred a month. The video itself is priced separately. 5. **Write the brief.** Write it like a brief to a videographer: what it is for, the length and shape, the camera move, what must not change, and the rule that matters most: **show me the price first, and don't generate until I approve**. Paste the brief. Write it like a brief to a videographer. What it is for, the length, the camera move, what must not change, and: show me the price first. ```text Turn Image 1 into a 5-second vertical clip for our Instagram and our product page. Slow push-in on the can, morning light moving across the window sill, a few condensation drops sliding down. Keep the FIELDNOTE label exactly as it is. No people, no music. Show me the model, settings and exact price first, and don't generate until I approve. ``` 6. **Send it to Milo.** Click the **arrow** to send it. 7. **Watch the credit meter.** Milo shows a live meter: **30 credits used / 250 maximum**. A request never spends more than its maximum, and these are Milo credits, not money from your wallet. Click the card when Milo has answered. Milo shows a live meter, with a maximum it never goes over. These are Milo credits, not your wallet. ### 3. Pick a model and get the quote 8. **Compare the models.** Milo picked three image-to-video models and priced one 5-second clip on each: **Wan 3**, 480p, **$0.33**; **FLUX 3 Draft**, 720p, **$0.39**; **Dreamina Seedance 2.0 Mini**, 480p, **$0.43**. It recommends FLUX 3 Draft for the sharper 720p. Six cents more for the higher resolution is worth it on a product page. Click the **FLUX 3 Draft** row. Three models, priced for one five second clip. Wan 3 at thirty three cents, FLUX 3 Draft at thirty nine, Seedance Mini at forty three. FLUX gives you 720p. 9. **Ask for the exact quote.** Read the honest part at the end: Milo will *instruct the model to [preserve](https://learn.ynteractive.com/content/glossary/condense-vs-preserve) the FIELDNOTE label, but animation cannot guarantee that the lettering remains pixel-exact*, and a 9:16 frame may crop the sides. These prices are estimates. Ask for the exact quote. Paste the reply. Read the honest part. Milo cannot promise the label stays pixel exact, and the vertical frame may crop the sides. These are estimates, so ask for the exact quote. 10. **Jump to the answer.** Your reply is sent. Click **Latest message** to jump down to Milo's answer. Your reply is sent. 11. **Open the direction.** This is the quote card: **Video, $0.39**, **FLUX 3 Draft · 9:16 · 720p · 5 s · silent · start frame**. Start frame means your photo is the first frame of the clip. The whole conversation used 70 Milo credits, about 7 cents of the included 500. Before you pay, read what Milo will actually send. Click **View direction and settings**. The quote card. Thirty nine cents, FLUX 3 Draft, vertical, 720p, five seconds, silent, and your photo as the first frame. Before you pay, read what Milo will send. 12. **Check the prompt.** This is the prompt Milo wrote for you: one slow push-in, shifting morning light, sliding droplets, and *Keep the can, its shape, color, label design and all label lettering exactly as in the source*. If anything is wrong, say so in the chat and ask for a new quote. It looks right, so click **View direction and settings** again to fold it away. This is the prompt Milo wrote. Push-in, morning light, droplets, and keep the label exactly. If anything is wrong, ask for a new quote. It looks right, so fold it away. 13. **Fund the wallet, then confirm.** On our first run the wallet was **$0.00**, and this card said *Insufficient balance*, with **Add funds** and **Refresh balance** buttons. That is the safety net: nothing is spent until you have funds and confirm. We added $10 and refreshed, and the card now reads **Available balance: $10.00** with one button, **Create video · $0.39**, *charged only when you confirm*. Top up only what you need, then click **Create video · $0.39**. On our first run the wallet was empty, and this card said insufficient balance. Nothing is spent until you add funds and confirm. We added ten dollars and refreshed. Now it says available balance, ten dollars, and one button: Create video, thirty nine cents. 14. **Watch the clip.** About a minute later the card says **Creation ready** and the clip appears under it. This is the real 5-second clip FLUX 3 Draft made from the photo on 9 November 2026, playing here: one slow push-in, the light on the sill, droplets on the can, and the **FIELDNOTE** label stayed sharp. The wallet went from $10.00 to **$9.61**, exactly the quote. Scrub every second before you post, because the label is the product. Click the clip to finish. About a minute later the card says creation ready, and the clip appears. This is the real five second clip, playing here. A slow push-in, droplets on the can, and the Fieldnote label stayed sharp. The wallet went from ten dollars to nine sixty one, exactly the quote. Check every second before you post. ## Frequently asked questions **Can MaxVideoAI turn a product photo into a video?** Yes. In Studio you add the photo as a reference and describe the clip. Milo picks an image-to-video model, uses the photo as the start frame and quotes the price before generating. **How much does a 5-second clip cost in MaxVideoAI?** In our tests on 6 and 9 November 2026, Milo quoted $0.33 to $0.43 for one 5-second vertical clip, depending on the model; FLUX 3 Draft at 720p was $0.39, and that is exactly what the wallet was charged when we generated it. Each generation shows its own quote first. **What is Milo in MaxVideoAI?** Milo is the Studio assistant. It reads your brief, chooses models, writes the prompt and prepares quotes. It runs on Milo credits, which are separate from the wallet that pays for the video. **Will the AI keep my product label exactly?** Not guaranteed. Milo tells the model to keep the label, but warned that animated lettering may not stay pixel-exact. In our FLUX 3 Draft clip the FIELDNOTE label stayed sharp, but check every clip before you post it. **Is this lesson free, and was it tested in the real app?** The lesson is free and the practice copy needs no account. Every step was done in a real MaxVideoAI account, and the clip in the last step is the one MaxVideoAI generated for $0.39 on 9 November 2026. [Start this module free](https://learn.ynteractive.com/modules/maxvideoai-product-photo-clip) - Previous in AI Automation for Marketing: [SocialBee: Turn Patient FAQs into an Evergreen TikTok Queue](https://learn.ynteractive.com/content/socialbee-tiktok-patient-faq-queue) - Next in AI Automation for Marketing: [TryPost: Turn One Blog Post into a Week of Scheduled Social Posts](https://learn.ynteractive.com/content/trypost-n8n-blog-post-to-week-of-social-posts) ## More in AI Automation for Marketing - [Build an n8n AI Agent That Plans Your Content Calendar](https://learn.ynteractive.com/content/n8n-ai-agent-content-calendar): Build an AI agent for Harbor & Pine Coffee Roasters that turns one campaign theme into a two-week email and content calendar in Google Sheets — chat trigger, AI Agent… - [Build a Lead Magnet Signup Form with an AI Welcome Email](https://learn.ynteractive.com/content/lead-magnet-signup-form-ai-welcome-email): Build a "Get the free guide" signup form in Lovable for Harbor & Pine Coffee Roasters and connect it to n8n — the AI agent tags each lead by interest, saves it to… - [Get Your Business Recommended by ChatGPT](https://learn.ynteractive.com/content/get-recommended-by-chatgpt): Ask ChatGPT who it recommends in your town, see which pages it trusts, then use it to write an FAQ page and Business Profile copy that answer real customer questions. - [iMini AI Agent: Turn a Rough Idea into a Launch Kit](https://learn.ynteractive.com/content/imini-ai-agent-marketing-launch-kit): Brief the iMini Creative Agent once and get a launch plan, a LinkedIn visual, a post and a 5-slide deck, then fix the visual and humanize the post with follow-ups. - [Post to Every Channel Daily from One Sheet using n8n + Blotato](https://learn.ynteractive.com/content/post-everywhere-from-google-sheets-n8n-blotato): Copying the same post into every social app can take half an hour a day, and on busy days nothing goes out. Plan a week of posts in one Google Sheet; every morning n8n… - [VisualGPT: Product Photos, Listing Images and Ads from One Phone Photo](https://learn.ynteractive.com/content/visualgpt-product-photos-listing-images-ads): Turn one phone photo into a lifestyle product shot, a five-image Amazon listing set and three launch ads in VisualGPT's Commercial Studio, checking the plan and every… [All 25 modules in AI Automation for Marketing](https://learn.ynteractive.com/content/industry/marketing) ## Terms in this lesson Plain-English definitions, each with an example from a free lesson. [Prompt](https://learn.ynteractive.com/content/glossary/prompt) · [AI credits](https://learn.ynteractive.com/content/glossary/ai-credits) · [Condense vs Preserve](https://learn.ynteractive.com/content/glossary/condense-vs-preserve) [The full AI glossary](https://learn.ynteractive.com/content/glossary) ## Browse related tutorials [AI for Marketing (25)](https://learn.ynteractive.com/content/industry/marketing)