Maple and honey gift box unboxing clip from two photos: $1.00
A small farm can show a gift box opening by giving Wan 3.0 a closed-box first frame and an open-box last frame. 8 seconds at 720p is $1.00 on Sume.

A small farm selling maple syrup or honey gift boxes can show the box opening by giving Wan 3.0 two photos, a closed box as the first frame and an open box as the last frame, and an 8-second clip at 720p costs $1.00 on Sume. The model fills in the motion between the two real photographs.
Gift boxes sell on the moment of opening. Shoppers cannot hold the box online, so a short clip of the lid lifting and the jars revealed does the work of a store counter. Using your own two photos keeps the contents accurate, which matters when the box is the product.
First frame and last frame
The Video Generation docs list Wan 3.0 as supporting image-to-video with an end frame, for 2 to 30 seconds. You supply the first image and the last image, and the model animates the transition. This is more controllable than text-to-video, since both ends of the clip are your photographs.
Photograph the two states from the same camera position on a tripod, with the same light and the same table. The more the two frames match except for the lid and the contents, the smoother the motion. If the box is on a different part of the table in each photo, the model will slide or morph it. Keep the jars in the open photo exactly as you will ship them.
- Same tripod position, same light, same surface for both photos.
- Closed box centered, open box centered, nothing else moved.
- Public HTTPS links for both images.
Cost
Wan 3.0 on Sume is provider list times 1.25: $0.0625 per second at 480p, $0.125 at 720p and $0.25 at 1080p (read 2026-10-10). An 8-second clip is $0.50 at 480p, $1.00 at 720p and $2.00 at 1080p. If you make one clip for each of four box sizes, at 720p the set is $4.00.
| Resolution | Per second | 8 s clip | Four boxes |
|---|---|---|---|
| 480p | $0.0625 | $0.50 | $2.00 |
| 720p | $0.125 | $1.00 | $4.00 |
| 1080p | $0.25 | $2.00 | $8.00 |
Words on the clip
Do not ask the model to write on the box or the labels. Generated text is unreliable. If the photo already has your label, the model may blur it as it moves. Keep your label on the jars legible by choosing a short duration and a calm motion, and add the product names with video captions cues if you need text on screen. That job is $0.20 per clip.
Setting up the two photos
Use a plain surface and soft window light. Shoot the closed box first with the ribbon tied, then untie the ribbon, lift the lid, and arrange the jars so that every label faces forward. Do not touch the camera between the two shots. A tripod and a timer on the phone are enough. Shoot at the highest quality your camera allows and export at a size a web upload accepts.
Then write a short motion prompt: "The ribbon loosens, the lid lifts away and the jars are revealed, slow and gentle, camera steady". If the first try shows the lid vanishing instead of lifting, run again at 480p for $0.50 and adjust the wording before spending $1.00 on the final. Keep two or three best takes for different channels.
Where to post and what to say
Post the clip on the product page and on your short-form feed in the weeks before the shipping cutoff. Put the cutoff date, the box contents and the price in the text. Avoid any claim about taste, purity or health that you cannot back with your own label. If the clip is going into an email, remember that many clients do not play video; use the first frame as the image and link to the clip.
Say what is on the label and nothing more. Do not make health claims about honey or syrup in a clip or its caption, and do not show a pour that looks like more product than the jar holds. Put weight, ingredients and shipping dates in text. For another example of short clips for a seasonal producer, see the farmers market weekly update post.
Sources
Related posts
More in Use cases
- Martial arts school belt-test notice: avatar clip with silent beats
A dojo can announce belt-test day with one Avatar 1.0 clip built from spoken scenes and a silence beat. A 24-second clip is $5.88 at plus tier.
- Meal prep weekly menu clip: 12 Mondays to year-end, 51 cents each
A meal-prep cook can post a weekly menu clip every Monday until Dec 28 for about $6.12 in total: an 8-second clip plus a text-to-speech line each week.
- Music teacher intro video: an avatar, cutaways and a 480p b-roll
Build a 20-second music lesson intro: one Avatar 1.0 talking video, audio detach as the spine, a Wan 3.0 cutaway and Timeline. Chain and cost, read 2026-10-10.
- New-hire welcome video: 30-second avatar with auto captions
A 30-second welcome video from an Avatar 1.0 talking video plus speech captions costs $5.72 on Sume. Chain, limits and English-only caveat, read 2026-10-10.
Written by Sume