--- title: Creator-style product video from a product image display: '*Creator-style* product video from a product image' nav_title: Creator-style video summary: - "A 13-second vertical creator video for an invented serum: a spoken line, the exact app screen, an end card." - "The featured UGC Apps returned 16:9 without speech in this run, so the vertical take runs on a video model directly." - "A repeat costs one first frame and one video take; the take is most of the cost, so preview at delivery size and keep a preview that passes." description: Turn a product image into a short vertical creator-style video with the UGC Apps or their models, then add the app screen, end card and button in code. section: playbooks order: 315 type: playbook topic: Brand and marketing level: Build roles: [marketer, creator] time: { read: 9, do: 45, wait: 14 } needs: ["Any plan with credits", "A product photo and an app screenshot", "ffmpeg and Python with Pillow, NumPy and SciPy for the assembly", "whisper for the transcript check (optional)"] last_verified: 2026-10-16 models_checked: ["Minimax H3", "Seedance 2.5", "Gemini Omni 1.1 Flash", "GPT Image 2.5 Sunburst"] hero: playbooks/creator-style-product-video/hero.webp related: [mobile-ua-video-ads, ad-variations-family, product-packshots, run-and-share-apps, product-lifestyle-scenes, key-art-and-store-assets] pdf: true run_in: [model_minimax-h3, model_bytedance-seedance-2-5, model_google-omni-1-1-flash, model_openai-gpt-image-2-5-sunburst] hero_in_header: true # the use case made, on scenario.com/explorations, and the platform workflows that run it made_with: - { slug: content-engine, title: "Content Engine" } run_with: - { id: wflow_1oqUWYGAaH4g3ToWBEApeVmV, name: "UGC Product Showcase" } - { id: wflow_ugc-product-demo, name: "UGC Product Demo" } thumb: playbooks/creator-style-product-video/thumb.webp video: tutorials/creator-style-product-video.mp4 chapters: - { at: 0, title: "The creator-style ad to make", image: "/media/images/playbooks/creator-style-product-video/ch-01-the-creator-style-ad-to-make.webp" } - { at: 27, title: "Start with the featured Apps", image: "/media/images/playbooks/creator-style-product-video/ch-02-start-with-the-featured-apps.webp" } - { at: 60, title: "A vertical first frame", image: "/media/images/playbooks/creator-style-product-video/ch-03-a-vertical-first-frame.webp" } - { at: 78.5, title: "The line goes in the prompt, in quotes", image: "/media/images/playbooks/creator-style-product-video/ch-04-the-line-goes-in-the-prompt-in-quotes.webp" } - { at: 114.5, title: "Paste the screen in code", image: "/media/images/playbooks/creator-style-product-video/ch-05-paste-the-screen-in-code.webp" } - { at: 128, title: "Captions, push-in, end card", image: "/media/images/playbooks/creator-style-product-video/ch-06-captions-push-in-end-card.webp" } - { at: 157, title: "Recap", image: "/media/images/playbooks/creator-style-product-video/ch-07-recap.webp" } steps: - title: "Start with the featured Apps" text: "Home › Featured Apps › UGC Product Showcase: add a person photo and a product photo. In this run the Apps came back wide, with music and no speech, so their method (a product composite, then a video) was rebuilt vertical with a spoken line." - title: "A vertical first frame" text: "Create › Images › GPT Image 2.5 Sunburst, Dimensions 9:16, Reference Images: the creator photo, then the serum packshot. Check the hand and the label on this still, before any video." prompt: |- Add the product held by the person. The woman from the first reference image (same face, long dark wavy hair, small pearl stud earrings, ivory linen shirt, same bright bathroom) holds the serum bottle from the second reference image up beside her face toward the camera in her right hand, as if showing it to a friend on a video call. The bottle keeps its exact look: frosted glass body, pearl-white rounded dropper bulb, satin pearl-silver collar, white label reading NACRE ATELIER, PEARL SERUM and 30 ml, label facing the camera. Relaxed natural grip with all fingers correct, the label not covered by her fingers, warm smile, looking into the camera. Authentic creator-style phone video framing, vertical, waist-up, natural daylight, casual and unposed. No other text anywhere. - title: "The line goes in the prompt, in quotes" text: "Create › Videos › Minimax H3, the approved still as First Frame, Duration 8, Resolution 768P. The line goes in the prompt in quotes; of three models tried, Minimax H3 kept the label readable." prompt: |- Creator-style vertical phone video. The woman holds the serum bottle up beside her face, smiles and says to the camera in a natural, warm voice: "Two drops every night. And my app keeps the streak." She tilts the bottle a little toward the camera so the label catches the light, then taps the pearl-white dropper bulb once with one finger. The label stays facing the camera and readable. Slight handheld phone-camera sway, natural daylight bathroom. The bottle keeps its exact shape, frosted glass and label. No on-screen text, no captions. Quiet bathroom ambience, no music. - title: "Paste the screen in code" text: "Never let a model draw the app screen: code finds the blank phone screen and pastes the real screenshot onto it, pixel for pixel." - title: "Captions, push-in, end card" text: "Code adds captions timed to the transcript, a push-in on the phone and an end card with a button. For the A/B test, variant B changes only the opening." agent_steps: - title: "Connect the Scenario MCP" text: "Connect your agent and sign in once at [mcp.scenario.com](https://mcp.scenario.com). Then tell it which Scenario team and project to use, so every file lands there." - title: "Give the agent the files" text: "The creator photo first, then the serum packshot, then the app screenshot. Upload them with upload_asset or give their asset IDs. A local agent also needs ffmpeg and Python with Pillow, NumPy and SciPy for the assembly, and whisper for the transcript check." - title: "Try the featured Apps first (optional)" text: "In this run the Apps came back wide, with music and no speech, so their method was rebuilt vertical with a spoken line. The App job itself shows no charge: the cost sits on its child jobs." prompt: |- Find the featured Apps with workflows_list (privacy "public", tags ["featured"]), read the inputs of UGC Product Showcase with workflow_get, and run it with workflow_run on the creator photo and the serum packshot. Quote it first and wait for my go. Tell me the format of the result and whether it has speech or music. - title: "Brief the agent: the first frame" prompt: |- Make a vertical first frame with GPT Image 2.5 Sunburst (model_openai-gpt-image-2-5-sunburst), 9:16, with referenceImages as an array: the creator photo first, the serum packshot second. Quote the cost with a dry run first and wait for my go. Prompt, word for word: Add the product held by the person. The woman from the first reference image (same face, long dark wavy hair, small pearl stud earrings, ivory linen shirt, same bright bathroom) holds the serum bottle from the second reference image up beside her face toward the camera in her right hand, as if showing it to a friend on a video call. The bottle keeps its exact look: frosted glass body, pearl-white rounded dropper bulb, satin pearl-silver collar, white label reading NACRE ATELIER, PEARL SERUM and 30 ml, label facing the camera. Relaxed natural grip with all fingers correct, the label not covered by her fingers, warm smile, looking into the camera. Authentic creator-style phone video framing, vertical, waist-up, natural daylight, casual and unposed. No other text anywhere. Show me the still. Before any video, check her hand (all fingers correct) and the label (NACRE ATELIER, PEARL SERUM, 30 ml, not covered by her fingers). - title: "Brief the agent: the video" text: "The spoken line goes in the prompt, in quotes. Of three models tried, Minimax H3 kept the label readable." prompt: |- Animate the approved still with Minimax H3 (model_minimax-h3): firstFrameImage set to the still, duration 8, resolution "768P". Quote it with a dry run first and wait for my go. Prompt, word for word: Creator-style vertical phone video. The woman holds the serum bottle up beside her face, smiles and says to the camera in a natural, warm voice: "Two drops every night. And my app keeps the streak." She tilts the bottle a little toward the camera so the label catches the light, then taps the pearl-white dropper bulb once with one finger. The label stays facing the camera and readable. Slight handheld phone-camera sway, natural daylight bathroom. The bottle keeps its exact shape, frosted glass and label. No on-screen text, no captions. Quiet bathroom ambience, no music. When it is back, transcribe it with whisper and compare the words with the line in quotes. - title: "Assemble in code and check" text: "Accept when the transcript matches the line, the bottle keeps its shape and its label reads in every close-up, fingers stay correct, and the screen matches the screenshot. Reject invented letters on the label, a second bottle, other words, a redrawn screen or music over the voice." prompt: |- Never let a model draw the app screen: find the blank phone screen in code and paste the real screenshot onto it, pixel for pixel. Add captions timed to the transcript, a push-in on the phone and an end card with a button. For the A/B test, make variant B with only the opening changed: it opens on the creator holding the phone screen. Check every close-up of the label and tell me any frame where it fails. - title: "File and report" prompt: |- Create a collection for this campaign with the first frame and the video take, and report the models, every asset ID, the paths of the two finished variants, the transcript and the total cost spent. updated: 2026-10-16 canonical: https://learn.scenario.com/playbooks/creator-style-product-video --- Last updated: 2026-10-16 # Creator-style product video from a product image > Turn a product image into a short vertical creator-style video with the UGC Apps or their models, then add the app screen, end card and button in code. In short: - A 13-second vertical creator video for an invented serum: a spoken line, the exact app screen, an end card. - The featured UGC Apps returned 16:9 without speech in this run, so the vertical take runs on a video model directly. - A repeat costs one first frame and one video take; the take is most of the cost, so preview at delivery size and keep a preview that passes. A vertical, creator-style video for the Pearl Serum of Nacre Atelier, an invented skincare brand, and its evening-ritual app. An invented creator says one line, the exact app screen appears, then an end card with a button. Plus a second cut for an A/B test. :::note As of October 2026 The models, settings and screens in this article are the ones Scenario offered in October 2026. New models and updates arrive often, so check the app for newer options before you choose. ::: :::video https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/051ba269aa2863e657d9f86250d234c0076f64c585b6c873615913246f53a336.mp4 Variant A, 13 seconds: a Minimax H3 take with a spoken line, then the app screen and the end card, both added in code. ::: ## The brief | Field | Brief | |---|---| | Goal | One vertical creator-style video and one test variant for a serum and its streak app | | Inputs | A creator photo, a product packshot, an app screenshot | | Format | 9:16, 720x1280, 30 fps, about 13 seconds, with the creator's voice | | Fixed | Bottle shape and finish (frosted glass, pearl-white dropper bulb), label text NACRE ATELIER, PEARL SERUM, 30 ml; app screen pixel for pixel; end card text | | May vary | Gestures, handheld sway, the order of the shots in the variant | | Accept when | The line is spoken word for word; hands and bottle hold in every frame; the label reads; the screen matches the screenshot; captions sit on the right words | ## Approach :::flow Inputs | creator, packshot, app screen in code | image Try the Apps | three featured UGC Apps | video Vertical first frame | the App's first step, at 9:16 | image Talking take | Minimax H3, line in the prompt | video Assemble in code | screen, captions, end card, button | ::: The Home screen lists three creator-style Apps under **FEATURED APPS**: **UGC Product Showcase**, **UGC Product Demo** and **UGC App Showcase**. They are the fastest route, so run them first. In this run, the two video Apps returned 16:9 clips with a music bed and no speech. So the playbook rebuilds the same chain in 9:16, with a scripted line, and picks the video model in a preview shoot-out. Anything that must be exact (screen, words, button) is done in code. - **Capability:** image to video with native speech. - **Model used:** Minimax H3 at 768P, the shoot-out winner: the line word for word and the label readable in close-up. GPT Image 2.5 Sunburst for the first frame, as in the App. - **Alternatives:** Seedance 2.5, the model inside **UGC Product Demo**: its draft preview turned the label into invented letters. Gemini Omni 1.1 Flash: native 9:16 and clean speech, but the label never read and the bottle left the frame at the end. What the models generate, and what code sets exactly: | Made by the models | Set in code | |---|---| | The creator holding the bottle in the vertical first frame | The app screen, pasted pixel for pixel onto the phone | | The gestures and the handheld sway | The captions, timed to the transcript | | The spoken line, in her voice | The push-in on the phone | | The label catching the light as she tilts the bottle | The end card and its button | | | The order of shots in the test variant | ## Steps :::steps 1. **Make the inputs.** An invented creator (waist-up, bright bathroom, hands empty at chest height, no products), the same creator holding a phone with a blank white screen, and the packshot from the brand's own phone photo of the bottle. GPT Image 2.5 Sunburst, one run each, 31 to 36 seconds. Draw the app screen in code. Name every product detail that must survive, label text included: ```prompt E-commerce packshot of the product in the reference image: the Nacre Atelier Pearl Serum, a frosted glass dropper bottle, 30 ml, with a pearl-white rounded dropper bulb and a short pearl-white collar, a clear glass pipette inside, and a small white rectangular label that reads exactly NACRE ATELIER on the first line, PEARL SERUM on the second line and 30 ml at the bottom, in fine dark grey serif capitals. Standing upright, three-quarter front view, centered, on a seamless pure white background with a soft natural contact shadow. Style: luxury beauty photography, crisp frosted glass, clean typography on pack. No other objects, no other text. ``` ![Creator photo, frosted serum packshot, creator holding a blank phone, and the app screen with a 21-night streak](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/ddc9613e0fb82bf4102c8957be3067331cd8346809af7c31bc9c2acee8dc4b11.webp "The four inputs. The app screen is drawn in code, not generated.") 2. **Run the three Apps** ([Quote before you run](https://learn.scenario.com/browse)). This run started them through the Scenario MCP (see below); in the web app, open each App from Home > **FEATURED APPS** and add the inputs. **UGC Product Showcase** (person, product): 3 minutes 37 seconds. **UGC Product Demo** (person, product): 6 minutes 48 seconds, the most expensive. **UGC App Showcase** (person photo, app screenshot): 32 seconds, a single image. ![Four frames from each video App: the creator holds the serum in a wide 16:9 bathroom shot and brings the dropper to her face](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/49938329adfd77e57e51281dfd5f84d2b2c53936e88bd8ba859a68c2ade905a5.webp "Both video Apps: 8 seconds, 16:9, a music bed but no speech.") 3. **Decide what to rebuild.** Both video Apps chain a Sunburst composite into an 8-second 16:9 video. Keep their method, change the shape and add the line. **UGC App Showcase** keeps the vertical shape but redraws the screen, and in this run it dropped Thursday from the week row: step 7 fixes that. 4. **Make the vertical first frame** ([Give each reference a role](https://learn.scenario.com/browse)). Sunburst at 1088x1920, creator and packshot as references, starting with the App's own first sentence. 31 seconds. Check the hand and the label before going further ([Approve the still first](https://learn.scenario.com/browse)). ```prompt Add the product held by the person. The woman from the first reference image (same face, long dark wavy hair, small pearl stud earrings, ivory linen shirt, same bright bathroom) holds the serum bottle from the second reference image up beside her face toward the camera in her right hand, as if showing it to a friend on a video call. The bottle keeps its exact look: frosted glass body, pearl-white rounded dropper bulb, satin pearl-silver collar, white label reading NACRE ATELIER, PEARL SERUM and 30 ml, label facing the camera. Relaxed natural grip with all fingers correct, the label not covered by her fingers, warm smile, looking into the camera. Authentic creator-style phone video framing, vertical, waist-up, natural daylight, casual and unposed. No other text anywhere. ``` ![The creator holds the serum beside her face in a vertical bathroom shot, fingers correct and label facing the camera](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/d3e3af189fa97d36b3d306be8c06fc5efc75291357dc2bc08f9dcbe9fca7f9d1.webp "The 9:16 first frame.") 5. **Preview three models on that frame** ([Run a same-input shoot-out](https://learn.scenario.com/browse)). 8 seconds, speech on, one prompt: Minimax H3 at 768P, Seedance 2.5 in draft mode (480p), Gemini Omni 1.1 Flash at 720p in 9:16. Watch the label and the hand frame by frame, and check the words with a transcript (`whisper take.mp4 --model base.en`). ```prompt Creator-style vertical phone video. The woman holds the serum bottle up beside her face, smiles and says to the camera in a natural, warm voice: "Two drops every night. And my app keeps the streak." She tilts the bottle a little toward the camera so the label catches the light, then taps the pearl-white dropper bulb once with one finger. The label stays facing the camera and readable. Slight handheld phone-camera sway, natural daylight bathroom. The bottle keeps its exact shape, frosted glass and label. No on-screen text, no captions. Quiet bathroom ambience, no music. ``` ![Three rows of four frames: H3 keeps the label readable in close-up, the Seedance draft turns it into invented letters, Omni keeps the bottle small and turned](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/4012c628c292f2838987dd706882f4b4be996b73b95fab6268656d465a6a0d81.webp "Frames at 25, 55, 75 and 95% of each preview, top of frame.") 6. **Keep the preview that passes** ([Animate from a first frame](https://learn.scenario.com/browse)). The H3 preview came back at 768x1344, above the 720x1280 delivery size, with the line word for word, the label readable and the hands correct. A rerun at a higher resolution would cost more for nothing the feed can show, so the preview is the final. 4 minutes 14 seconds. In the web app: **Create** > **Videos**, **Model** Minimax H3, the frame in **First Frame**, **Duration** 8 s, **Resolution** 768P; the price shows on the **Generate** button first. Minimax H3 always adds sound: here, her voice and a quiet room. 7. **Paste the exact screen in code** ([Do the exact part in code](https://learn.scenario.com/browse)). Find the white screen in the phone photo, fit its four corners, and warp the screenshot onto it. Shrink the screenshot first with a high-quality filter to avoid jagged text; for the push-in, upscale the photo 2x before pasting so the screen stays sharp up close. ```python white = (P.min(axis=2) > 236) & (np.ptp(P, axis=2) < 14) # blank screen pixels # largest tall blob -> corners tl, tr, br, bl -> perspective coefficients warped = screen.transform(photo.size, Image.PERSPECTIVE, coeffs, Image.BICUBIC) ``` ![The App's phone screen next to the code paste: the App's week row shows six days, the paste shows all seven](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/a793ca15e3796a31ee63fe11e386e900f344e88df7a8c7740542a9252de8661d.webp "Left: UGC App Showcase redraws the screenshot and drops a day. Right: pasted in code, pixel-exact.") 8. **Assemble in code** ([Typeset text, never generate it](https://learn.scenario.com/browse), [Conform clips before the edit](https://learn.scenario.com/browse)). Conform the take to 720x1280 at 30 fps. Add two captions timed to the transcript, a 2.5-second push-in on the phone ("21 nights, logged in the app"), then a 2.5-second end card. Draw the button on its own layer: it slides in at 0.35 s and pulses at 1.3 s. ```bash ffmpeg -i take.mp4 -vf "scale=720:1280:force_original_aspect_ratio=increase,crop=720:1280,fps=30" take-720.mp4 ``` 9. **Cut the test variant** ([Edit one thing](https://learn.scenario.com/browse)). Variant B uses the same shots and end card, with the app shot first. One difference only, so the test result points at the hook. ![First second of each variant: A opens on the creator with the serum, B on the creator holding the phone screen](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/acaec0f75c7e5be8938b5a4dd42f13b5c31ab63e1390f4c94dbbd05d9d7c986a.webp "Variant A opens on the creator, variant B on the app screen.") ::: **With the Scenario MCP:** `workflows_list` with `privacy: "public"` and `tags: ["featured"]` finds the Apps; `workflow_get` lists their inputs; `workflow_run` runs them. The App job itself shows no charge: the cost sits on its child jobs. The final: `model_run` on `model_minimax-h3` with `firstFrameImage`, `duration: 8`, `resolution: "768P"`; ask for a dry-run quote first. ## Check the result :::check **Accept when:** the transcript matches the line; the bottle keeps its shape and its label reads in every close-up; fingers stay correct; the screen matches the screenshot; captions change on the right words; the button stays readable on a phone. **Reject when:** the label turns into invented letters; a second bottle appears; the voice says other words; screen text is redrawn; music covers the voice. ::: | Vertical preview, 8 s | Wait | Product | Speech | |---|---|---|---| | Minimax H3, 768P | 4 min 14 s | label readable in close-up, hands correct | line word for word, winner | | Seedance 2.5, draft 480p | 1 min 37 s | label turns into invented letters | | | Gemini Omni 1.1 Flash, 720p | 50 s | label never reads; bottle leaves the frame at the end | clean | | App (one run each, October 2026) | Output | Speech | Wait | |---|---|---|---| | **UGC Product Showcase** | 8 s, 16:9, an older fast Seedance model; label roughly holds, background drifts | none, music bed | 3 min 37 s | | **UGC Product Demo** | 8 s, 16:9, Seedance 2.5; a second bottle appears and the label garbles | none, music bed | 6 min 48 s | | **UGC App Showcase** | still, keeps the input shape; screen redrawn, one weekday missing | | 32 s | Transcript of the final: "Two drops every night, and my app keeps the streak." The take ran 8.0 seconds at 768x1344. The finished video runs 13.0 seconds. :::video https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/03ff66d4662414c236ba636becedf309f223db80be7a93553e5ca82b5c320cab.mp4 Variant B: the same shots and end card, with the app shot first. ::: :::video https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/11d1def6146436a64a2b9becbaa91008856576232de163cb20b7c0f786f64de9.mp4 The **UGC Product Demo** output as it came: 16:9, a music bed and no speech. Watch the second bottle: rejected even for a web banner. ::: :::quiz Check yourself ? The phone screen must match the app screenshot pixel for pixel. Two versions of the screen on the creator's phone. Which one goes into the video? ![Two versions of the evening-ritual app screen on the creator's phone, side by side](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/a793ca15e3796a31ee63fe11e386e900f344e88df7a8c7740542a9252de8661d.webp "Left: Take A. Right: Take B") - [ ] Take A: it sits naturally in the photo, and small text differences will not show on a phone - [x] Take B: its layout, text and week row are the screenshot's own pixels - [ ] Either one: the captions cover most of the screen > Redrawn screen content is a reject. The App redrew the screenshot and dropped Thursday from the week row; pasting it in code keeps it exact. ? The transcript of a take reads "Two drops a night, and the app tracks it." The bottle and hands hold in every frame. What do you do? - [ ] Keep it: the meaning is the same and the product holds - [ ] Keep it and write the scripted line in the captions instead - [x] Reject it, run another take with the line short and in quotes, and check its transcript > The brief asks for the line word for word, and a voice saying other words is a reject. ::: ## Make it repeatable - **Build the vertical chain once.** In the **Node Editor**: two **Image** nodes (creator, packshot), an **Image Generator** on GPT Image 2.5 Sunburst at 1088x1920 with the step 4 prompt, a **Video Generator** on Minimax H3, and an **Approval** before the video. Publish it as an App ([Publish a workflow as an App](https://learn.scenario.com/workflows/publish-a-workflow-as-an-app.md)). - **Or start from the featured App.** In its editor, **Duplicate Workflow** and change the sizes and the video model on its generators. - **Keep the assembly as a script** with the variant as an argument: A or B, the caption lines, the button text. - **Test one change at a time:** the hook order, then the line, then the end card. ## Runs and time | Step | Model | Runs | Wait | |---|---|---|---| | Creator, phone photo, packshot | GPT Image 2.5 Sunburst | 3 | 31 to 36 s, in parallel | | Three UGC Apps | Sunburst, an older fast Seedance model, Seedance 2.5 | 3 Apps | 6 min 48 s, in parallel | | Vertical first frame | GPT Image 2.5 Sunburst | 1 | 31 s | | Vertical previews, 8 s | Minimax H3, Seedance 2.5 draft, Gemini Omni 1.1 Flash | 3 | 4 min 14 s, in parallel | | Final | the H3 preview, kept | 0 | none | | Screen paste, assembly, variant | Python, ffmpeg | | about 3 min | Ten runs, about 12 minutes of wait. The video runs (Apps and previews) are nearly all the cost; a repeat needs only the first frame and one take. Read the price on the **Generate** button, or ask for a dry-run quote, before each video. ## Variations - **Lip balm or a fragrance:** same chain, with the label text and the fragile parts in the keep-list of each prompt. - **App only:** **UGC App Showcase** for the framing, then the code paste for the screen. - **Web banner:** a 16:9 App output, if its product holds in every frame. - **Another market:** rerun the take with the line in another language and check it against a transcript ([Lip-sync and talking avatars](https://learn.scenario.com/courses/video-production)). - **More hooks:** a question as the first caption, or the label close-up first; one change per variant. ## If it breaks - **The App output is the wrong shape or silent.** Rebuild its chain with the models directly, as in steps 4 to 6. - **The label turns into invented letters.** Ask for the label "facing the camera and readable", preview at delivery size, and keep the model that holds it. - **A second product appears.** Reject the take; say "only one bottle" and keep the product in one hand. - **Wrong words.** Keep the line short, in quotes, and check every take with a transcript. - **Fingers go wrong.** Fix it on the first frame, before the video. - **Screen content drifts.** Never let a model draw the screen; paste it in code. - **Music under the voice.** Ask for "quiet ambience, no music"; the App takes come with a music bed. Source: https://learn.scenario.com/playbooks/creator-style-product-video