Mixer AI
HappyHorse 1.1
A short scene with sound, from text, a starting image or a set of photos.
When to choose it
Try HappyHorse 1.1 when your character and setting come from reference photos. Animate one image or assign separate references to the person, product and location. Keep the brief focused: a short clip needs one complete event, not every detail of a campaign.
- A dedicated reference mode works with several photos.
- Direct the picture and soundscape as one scene.
Modes and settings
- Text, one image or references with up to 9 photos.
- 3–15 seconds at 720p or 1080p, with a choice of aspect ratios.
Price in coins
| Quality / size | Input | Coins / second |
|---|---|---|
| 720p | First frame | ≈ 20.24 |
| 720p | References without video | ≈ 20.24 |
| 720p | Text | ≈ 20.24 |
| 1080p | First frame | ≈ 26.71 |
| 1080p | References without video | ≈ 26.71 |
| 1080p | Text | ≈ 26.71 |
Billing is per second, not per fixed-length clip. The rate is multiplied by the billable duration; the complete request total is rounded up to a whole coin once.
≈ marks a fractional rate rounded to two decimal places for display; billing uses full precision.
What you can make
- A character handling a product in a specified location.
- A short vertical episode for a promotional story.
How to direct the result
- Say which file supplies the character, product and environment.
- Match sound to the action: paper rustling, a lid clicking or one short line.
Example: opening a present
6 seconds. The character in photo one sits at a table in the room from photo two and opens the small box in photo three. They look inside and smile. Locked camera, slightly angled from the front. Preserve clothing and box color. Paper rustling and quiet room ambience, no music.
What to keep in mind
- More photos do not guarantee preservation of every small detail.
- Inspect hand-object contact and speech synchronization separately.
Sources
- Prices and availability — Mixer AI catalog, updated 2026-09-18.
- Official maker site: HappyHorse
Model facts verified: 2026-09-20.
FAQ
Are references required?
No. Text mode creates a scene without files.
How many photos can I use?
Up to nine in reference mode. Two or three may be enough for a simple action.
Can I exceed fifteen seconds?
Not in one request. Split the story into separate moments.
Do I need recorded speech?
Describe generated sound in the prompt. This is not a tool that requires an audio file for lip-sync.
Can I make a vertical clip?
Yes. Select the intended ratio before preparing composition and references.
How do I avoid mixing two characters?
Give each a separate photo, position and action. Avoid referring to both with the same ambiguous pronoun.
What changes the price?
The coin rate per second depends on quality, mode and, for some models, sound. Multiply it by the billable duration. Where input video is charged, its duration also counts. The complete request total is rounded once.
Do I need a separate model subscription?
No. In Mixer AI, you top up one coin balance and use it for the tasks you need. You do not need a separate subscription to this model.