Product ad video from one photo
To make a product ad video with AI, upload a photo of the pack as the first frame, describe the camera move, light and background, and pick a model. ClickBait runs this on Kling, Seedance, Veo, WAN and MiniMax H3. Kling, Seedance and Veo 3.1 Fast and Quality can also end the clip on a packshot set as the last frame. Kling 3.0 and WAN 3.0 generate sound, and the Voiceover and Music sections cover narration and a soundtrack.
Updated:
Which models make product videos
| Version | Developer | Modes | Duration | Resolution | Aspect ratios | Sound | References | Prompt | Features | Price from |
|---|---|---|---|---|---|---|---|---|---|---|
| Kling 3.0 | Kling | text to video, image to video, first and last frame | 3-15 s | 720p, 1080p, 4K | 16:9, 9:16, 1:1 | on/off switch | no references | up to 2,500 characters | from 20 tokens | |
| Kling 3.0 Omni | Kling | text to video, image to video, first and last frame, reference images, video edit | 3-15 s | 720p, 1080p, 4K | 16:9, 9:16, 1:1 | on/off switch | up to 7 images, up to 1 videos | up to 2,500 characters | from 20 tokens | |
| Seedance 2 | ByteDance | text to video, image to video, first and last frame, reference images, video edit | 4-15 s | 480p, 720p, 1080p, 4K | 9:16, 16:9, 1:1, 3:4, 4:3, 21:9 | on by default | up to 9 images, up to 3 videos | accepts an audio reference; video references work in text to video mode; 21:9 available | from 23 tokens | |
| Seedance 2 Fast | ByteDance | text to video, image to video, first and last frame, reference images, video edit | 4-15 s | 480p, 720p | 9:16, 16:9, 1:1, 3:4, 4:3, 21:9 | on by default | up to 9 images, up to 3 videos | accepts an audio reference; video references work in text to video mode; 21:9 available | from 18 tokens | |
| Seedance 2 Mini | ByteDance | text to video, image to video, first and last frame, reference images, video edit | 4-15 s | 480p, 720p | 9:16, 16:9, 1:1, 3:4, 4:3, 21:9 | on by default | up to 9 images, up to 3 videos | accepts an audio reference; video references work in text to video mode; 21:9 available | from 12 tokens | |
| Seedance 2.5 | ByteDance | text to video, image to video, first and last frame, reference images, video edit | 4-30 s | 480p, 720p, 1080p | 9:16, 16:9, 1:1, 3:4, 4:3, 21:9 | on by default | up to 30 images, up to 10 videos | accepts an audio reference; video references work in text to video mode; 21:9 available | from 33 tokens | |
| Veo 3.1 Fast | text to video, image to video, first and last frame | 8 s | 720p, 1080p, 4K | 9:16, 16:9, 1:1, 3:4, 4:3 | no switch | up to 1 images | up to 1,000 characters | from 63 tokens | ||
| Veo 3.1 Lite | text to video, image to video | 8 s | 720p, 1080p | 9:16, 16:9, 1:1, 3:4, 4:3 | no switch | up to 1 images | up to 1,000 characters | from 32 tokens | ||
| Veo 3.1 Quality | text to video, image to video, first and last frame | 8 s | 720p, 1080p, 4K | 9:16, 16:9, 1:1, 3:4, 4:3 | no switch | up to 1 images | up to 1,000 characters | from 250 tokens | ||
| WAN 3.0 | Alibaba | text to video, image to video, reference images | 2-30 s | 480p, 720p, 1080p | 9:16, 16:9, 1:1, 3:4, 4:3 | on by default | up to 10 images, up to 5 videos | up to 20,000 characters | accepts an audio reference | from 8 tokens |
| WAN 3.0 Prime | Alibaba | text to video, image to video, reference images | 2-30 s | 480p, 720p, 1080p | 9:16, 16:9, 1:1, 3:4, 4:3 | on by default | up to 10 images, up to 5 videos | up to 20,000 characters | accepts an audio reference | from 11 tokens |
| MiniMax H3 | MiniMax | text to video, image to video, reference images | 5-15 s | 768p, 2K | 9:16, 16:9, 1:1, 3:4, 4:3 | no switch | up to 9 images, up to 3 videos | picks the mode from your attachments | from 24 tokens |
How to make a product ad video
Prepare the frame
You need a sharp shot where the pack is large and the label is readable. You can swap the background first in the Photo section, and the To video button sends the finished picture over as the first frame.
Describe the scene
What the camera does, the light and background, what happens to the product and how it all ends. One clear action per clip beats five at once.
Set the ending and the format
If the model takes a last frame, put the packshot there. Pick the aspect ratio for the platform and the duration for the action.
Run and compare
The token cost is on the button before you start. Make a couple of versions with different camera moves and keep the one where the pack looks closest to the original.
Scenes that work in product ads
- Pack rotation: the product turns slowly on a pedestal, or the camera circles it in an arc. For a full turn, attach shots of the back and sides, or the model will make them up.
- Product in hand: a hand picks a bottle up from the table, turns the label to the camera and presses the pump.
- Unboxing: the box lid lifts, the product lies inside, the camera moves in closer.
- Before and after: the starting state as the first frame and the result as the last, such as a wrinkled shirt and the same shirt after a steamer. This scene needs a model with a last frame.
- Ingredients around the pack: berries, coffee beans or mint leaves swirl around it, and drops run down a cold bottle.
- Product in use: steam over a mug, sneakers on wet asphalt, a jar of cream on a bathroom shelf in the morning.
How to write a prompt for a product ad
Build the prompt in order: the product and where it stands, the camera move, the light, the background and the ending. One camera move is enough: a slow push in, an arc around the product, a tracking shot along the side or a move down from above. Describe the light the way a photo studio would: soft and diffused, backlight, a highlight on glass, warm sunset light.
Example: "A serum bottle stands on light marble. The camera slowly circles it from left to right, soft studio light, a highlight slides across the glass, petals fall around it. The bottle shape and the label text stay unchanged."
Watch the prompt limit: up to 1,000 characters on Veo, 2,500 on Kling and 20,000 on WAN 3.0. Give a short clip one action, and list the steps in order for a longer one: a close-up of the label first, then the camera pulls back, and the packshot at the end.
How to keep the pack and the label intact
The model knows only what it sees in the photo and makes up the rest. So use a sharp shot for the first frame, with no glare across the label. With a fast camera move, small print is the first thing to blur, so show the label in a slow shot.
Set the same packshot or a shot from another angle as the last frame: the ending then rests on your picture rather than on a guess. A last frame works on Kling 3.0, Kling 3.0 Omni, Veo 3.1 Fast and Quality, and every Seedance version. For turns, attach photos of the other sides as references: up to 30 on Seedance 2.5, 10 on WAN 3.0, 9 on the other Seedance versions and MiniMax H3, and 7 on Kling 3.0 Omni counting the frames.
Say plainly in the prompt that the shape, color and text on the pack stay the same. A price, a discount or a call to action is safer to place over the finished clip than to ask the model to draw it in the frame.
Aspect ratios for each platform
- 9:16: full-screen vertical for Reels, Shorts, TikTok and stories. Every model has it.
- 1:1: a square for feeds and carousels, also on every model.
- 16:9: horizontal for YouTube, a website or a presentation. Every model has it.
- 3:4 and 4:3: a frame a little narrower or wider than a square, for a feed or a product card. Every model except Kling.
- 21:9: a wide cinematic frame for a website header, Seedance only.
- Prepare the starting photo in the aspect ratio of the clip, so the model does not have to crop the product or invent the edges.
Sound, voiceover and music
Kling 3.0 and Kling 3.0 Omni generate sound with a switch, and WAN 3.0 has it on by default. Seedance, Veo and MiniMax H3 have no sound switch.
Generate the narration in the Voiceover section with ElevenLabs, Minimax Speech-02 HD or Seed Audio 1.0. Suno writes the background music in the Music section, and for an ad it helps to turn on instrumental mode to get a track with no vocals.
The To video button on a track sends it from Music to the composer as an audio reference, and a voiceover can be uploaded there as a file. Seedance and WAN 3.0 accept that kind of sound. If a person talks about the product on camera, pass the track to Lip sync so the lips follow the speech.
More tools for product ads
Where to find it in ClickBait
Product ad video lives in ClickBait under the Video section. Sign up, pick a version from the model list and describe what you want to get.
The token price is shown on the run button before you start. If a generation fails, the tokens go back to your balance automatically.
New accounts created with Google or email get a welcome bonus of 10 tokens. These are promo tokens and expire after 14 days.
Models for this task
Kling
video 3-15 s; matches the source video, up to 4K
images up to 4K
up to 10 references
from 2 tokens
Seedance
video 4-30 s, up to 4K
from 12 tokens
Veo
video 8 s, up to 4K
from 32 tokens
WAN
video 2-30 s, up to 1080p
up to 4 references
from 2 tokens
MiniMax H3
video 5-15 s, up to 2K
from 24 tokens
Other tools
AI video generator
12 models
Kling, Seedance, Veo, WAN, MiniMax H3
from 8 tokens
Image to video
13 models
Kling, Kling Motion Control, Seedance, Veo, WAN, MiniMax H3
from 8 tokens
AI image generator
18 models
Kling, Nano Banana, GPT Image, Seedream, FLUX, WAN, Z-Image
from 2 tokens
AI voiceover
5 models
ElevenLabs, Minimax Speech-02 HD, Seed Audio 1.0
from 2 tokens
Lip sync
5 models
Lipsync 2, Lipsync 2 Pro, Lipsync 3, InfiniteTalk, LatentSync
from 4 tokens
AI music generator
9 models
Suno
from 5 tokens
Video upscaler
1 model
Upscale
from 2 tokens
AI UGC video
12 models
Kling, Seedance, Veo, WAN, MiniMax H3
from 8 tokens
Creatives for affiliate marketing
30 models
Kling, Seedance, Veo, Nano Banana, GPT Image, Seedream, FLUX, WAN, MiniMax H3, Z-Image
from 2 tokens
Marketplace product photos
17 models
Kling, Nano Banana, GPT Image, Seedream, FLUX, WAN
from 2 tokens
Videos for TikTok and Reels
12 models
Kling, Seedance, Veo, WAN, MiniMax H3
from 8 tokens
Ad posters and banners
17 models
Kling, Nano Banana, GPT Image, Seedream, FLUX, WAN, Z-Image
from 2 tokens
Frequently asked questions
Can I animate a product photo without a shoot?
Yes. Upload the photo as the first frame in the Video section and describe the motion: the model builds the clip from that frame. You do not need a studio or a camera crew: one clear shot of the pack is enough.
How do I keep the text on the pack from warping?
Use a sharp photo with a large label, pick a slow camera move and say in the prompt that the text stays unchanged. Set the same packshot as the last frame so the ending rests on your picture.
Can I put the product in a new scene?
Yes, in two ways. Build the frame in the Photo section, where models that edit from a photo place the product on a new background, and send it over as the first frame with the To video button. Or attach product photos as references and describe the scene in text: Kling 3.0 Omni, Seedance, WAN 3.0 and MiniMax H3 work this way.
How long can the video be?
Veo 3.1 always renders 8 seconds. Kling 3.0 and Kling 3.0 Omni go from 3 to 15 seconds, Seedance 2 from 4 to 15 and MiniMax H3 from 5 to 15. The longest clips, up to 30 seconds, come from Seedance 2.5 and WAN 3.0.
Will the video have sound?
Kling 3.0 and Kling 3.0 Omni turn sound on with a switch, and WAN 3.0 has it on by default. Make the narration in the Voiceover section and the music with Suno in the Music section; Seedance and WAN 3.0 take a ready track as an audio reference.
Will the video work for a marketplace product card?
Yes, if the aspect ratio and length fit the platform rules. Choose from 9:16, 3:4, 1:1, 4:3 and 16:9; Kling offers only 9:16, 16:9 and 1:1. Check the length and file size limits in your marketplace guidelines.
What resolution will the video be?
Up to 4K on Kling 3.0, Kling 3.0 Omni, Seedance 2 and Veo 3.1 Fast and Quality, up to 1080p on WAN 3.0 and Seedance 2.5, 768p or 2K on MiniMax H3. You can raise a finished clip to 2K or 4K with the upscaler in the Post-processing section.
How much does a product ad video cost?
You pay in tokens: the total depends on the model, length, resolution and sound and is shown on the button before you run. If the generation fails, the tokens go back to your balance.