Magic Hour — AI Video & Image Generation
Pricing
Pay per usage
Magic Hour — AI Video & Image Generation
Generate and edit video and images with Magic Hour's models — text-to-video, image-to-video, talking photo, character replace and instruction-based image editing.
Pricing
Pay per usage
Rating
0.0
(0)
Developer
Muhammad Ali Hashar
Maintained by CommunityActor stats
0
Bookmarked
1
Total users
0
Monthly active users
5 days ago
Last modified
Categories
Share
Generate and edit video and images with Magic Hour models, directly from Apify.
What it does
| Model | Does | Inputs | Output |
|---|---|---|---|
magic-hour/video-1 | Flagship and hero launch. Strongest self-hosted general video retentio | text, image | video |
magic-hour/image-editor-1 | Best evidence at scale and a large existing Magic Hour workflow. | text, image | image |
magic-hour/talking-photo-1 | Clear, highly demonstrable output. Highest measured Talking Photo D1. | text, image, audio | video |
magic-hour/character-replace-1 | Differentiated capability that general video models do not reliably re | video, image | video |
magic-hour/video-1-fast | Price and latency wedge. Initial engine selection must be confirmed by | text, image | video |
Input
| Field | Type | Notes |
|---|---|---|
model | string | One of the aliases above. Required. |
prompt | string | What to generate, or the edit instruction. |
imageUrl | string | Required for image-to-video, image edit, talking photo, character replace. |
videoUrl | string | Required for character replace and video-to-video. |
audioUrl | string | Optional drive audio for talking photo. |
durationSeconds | integer | Video models only. |
resolution | string | Must be supported by the chosen model. |
aspectRatio | string | Must be supported by the chosen model. |
seed | integer | Optional; reproduces a run. |
batch | array | Many generations in one run; each item overrides the top-level fields. |
Example:
{"model": "magic-hour/video-1","prompt": "Camera slowly panning right over a misty pine forest at dawn","durationSeconds": 5,"resolution": "1080p","aspectRatio": "16:9"}
Output
One dataset item per generation:
{"model": "magic-hour/video-1","revision": "2026-09-04-minimax-h3-a","status": "success","outputUrl": "https://...","inputMode": "i2v","durationSeconds": 5,"resolution": "1080p","aspectRatio": "16:9","totalMs": 96214,"failureReason": null}
The generated file is also stored in the run's key-value store under
OUTPUT-<n> so you can link to it directly.
Pricing
Pay per event. You are charged once for the run starting, then per second of generated video (or per generated image) — only for generations that actually succeed. Failed, moderation-blocked and invalid-input generations are not charged.
- Actor start — $0.002
- Magic Hour Video 1 — per video second — $0.5
- Magic Hour Image Editor 1 — per image — $0.04
- Magic Hour Talking Photo 1 — per video second — $0.3
- Magic Hour Character Replace 1 — per video second — $0.6
- Magic Hour Video 1 Fast — per video second — $0.12
Notes
- Model names are stable. When Magic Hour improves the implementation behind
magic-hour/video-1, the name does not change; therevisionin the output does. Log the revision if you need reproducibility. - Long videos take minutes. Set the run timeout accordingly.
Support
- Bugs and feature requests — open an issue on the Issues tab of this Actor. That is the fastest route and it is tracked.
- Questions about the models, prompting, credits or your Magic Hour account — support@magichour.ai
- Community — the Magic Hour Discord: https://discord.gg/JX5rgsZaJp
Your API key
This Actor never uses anyone else's key. Yours is an encrypted input, decrypted only inside your own run, and generations bill your own Magic Hour account. Run it without a key to see the model catalog without generating anything.