Turn phone footage into an ad-ready AI video

What you'll make

A checked final video that follows the source workflow and is ready for export.

Who this is for

Creators, marketers, founders, and small teams producing short AI-assisted videos from source media.

Step by step

Run the workflow

01
The full workflow behind how I made this exact video
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
1. Follow the shown setup, keep the source order unchanged, and run one controlled test.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
02
Prepare the source material
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
1. Capture as many images as you need, no pro camera gear required.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
03
Open DirectorGPT
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
1. Your Personal Director
2. We eliminate the guesswork from prompt engineering. This CustomGPT is calibrated to generate cinematic, ad-ready prompts optimized specifically for NanoBanana Pro.
3. The CustomGPT functions as your Creative Director. It builds structured concepts and converts them into production-ready prompts.
Check the prompt field, reference order, and visible settings.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
04
Upload the source to DirectorGPT
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
- Click here to open ChatGPT (opens in a new tab)Direct link supplied in the source. Source page 6.
1. Let's get started.
2. Open the CustomGPT (DirectorGPT):
3. Open the DirectorGPT using the link above. 1
4. Upload your image into the DirectorGPT.
5. (Optional) Add the dish name + 1-2 lines describing what it is. This helps the AI stay accurate.
6. You'll receive 4 ad concepts with copy-paste prompts.
Check the selected files and their order before continuing.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
05
The DirectorGPT generates 4 ad concepts from your image and description
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
1. Review the 4 concepts and choose one to produce. If needed, ask for more variations in the same style.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
06
Open the image generator
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
- Click here to open Google Flow (opens in a new tab)Direct link supplied in the source. Source page 8.
1. With your assets ready and your DirectorGPT prompts in hand, it's time to turn your phone photos into commercial-looking ad frames.
2. Go to Google Flow and select "Create with Flow."
3. Select + New project
Check the prompt field, reference order, and visible settings.
Check the prompt field, reference order, and visible settings.
Check the prompt field, reference order, and visible settings.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
07
Upload the source image
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
1. You may receive free credits (varies by account).
2. Upload your source image.
Check the selected files and their order before continuing.
Check the selected files and their order before continuing.
Check the selected files and their order before continuing.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
08
Copy the selected prompt from DirectorGPT and paste it into Google Flow
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
1. Follow the shown setup, keep the source order unchanged, and run one controlled test.
Use this source result as the visual comparison point for the step.
Use this source result as the visual comparison point for the step.
Use this source result as the visual comparison point for the step.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
09
Generate the video
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
1. Now bring your ad frame to life in Kling AI. Precision here helps the model match your intended commercial look.
2. Open Kling AI → click Generate → choose Video Generation (Video 3.0). 1
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
10
Upload your original image into First Frame, and your generated image into Last Frame
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
1. Add a simple motion prompt. Need more control? Ask DirectorGPT for an advanced prompt.
2. Set your resolution, duration, and number of outputs then click Generate.
Use this source result as the visual comparison point for the step.
Use this source result as the visual comparison point for the step.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
11
Review the final result
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
- Click here to open Kling AI (opens in a new tab)Direct link supplied in the source. The Workflow Lab may earn a commission. Source page 13.
1. Final result: your original image transformed into an ad ready AI version. 5
2. OPERATIONAL NOTES:
3. Quality control: This workflow is optimized for Professional Mode. Standard/Free modes may produce lower resolution or unstable motion (jitter).
4. Get the Tools Here
5. Let's continue to the next phase
Use this source result as the visual comparison point for the step.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
12
Set the edit rhythm
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
1. Raw AI footage is your base. Post-production is where it becomes cinematic.
2. Temporal Remapping (Speed Ramps):
3. Use speed curves to create rhythm and emphasize key moments.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Use this visual to confirm the expected setup or result.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
13
Grade the colour
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
1. Visual Enhancement: Glow
2. Apply a "Soft Glow" or "Edge Glow" effect to simulate high-end lens diffusion and luxury aesthetics.
3. Color Grading: The Final Look
4. Final color adjustments allow you to refine the mood beyond the AI's base
Use this source result as the visual comparison point for the step.
Use this source result as the visual comparison point for the step.
Use this source result as the visual comparison point for the step.
Use this source result as the visual comparison point for the step.
Use this source result as the visual comparison point for the step.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
14
Polish and export the final edit
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
- Click here to open CapCut (opens in a new tab)Direct link supplied in the source. The Workflow Lab may earn a commission. Source page 16.
1. Polish is what makes it feel expensive. Fine-tuning is what maximizes impact and gives your commercial a premium finish.
Use this visual to confirm the expected setup or result.
Human check
Watch the result once at normal speed and once frame by frame. Check the subject, camera, timing, text, and scene continuity.
Common failure modes
- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.