Pika Camera Director vs a prompted video edit on Sume
Pika Camera Director reshoots a scene from new angles. On Sume, Omni Flash 1.1 edits a clip from a video_url and a prompt; there is no camera-angle parameter.

Pika's Camera Director reshoots an existing scene from new angles, from extreme wide to close-up, while preserving the scene. Sume has no camera-angle parameter. The closest documented route is a video edit on gemini-omni-flash-1.1: send your clip as video_url and describe the change in the prompt.
Pika's description is from its September 17 post; Sume's edit rules are from Video Router, read 2026-10-01.
What does Camera Director claim?
Only what the post's one-line summary says: reshoot an existing scene from new angles while preserving the scene itself. It gives no limits, input sizes or pricing, so none are compared here.
How does a video edit work on Sume?
Gemini Omni Flash 1.1 is one catalog id that Sume routes by the shape of the request. Sending video_url selects the video_to_video edit: the prompt describes the edit, resolution is optional with a 720p default, and aspect_ratio and duration are not accepted on an edit. video_url is the edit source, not a reference, so it cannot be combined with image_url, end_image_url or reference_*_urls.
| Field | On an edit call |
|---|---|
video_url | Required; the clip to change |
prompt | Describes the edit |
resolution | Optional, default 720p; model range is 360p, 720p, 1080p, 4K |
aspect_ratio, duration | Not sent |
image_url, reference_*_urls | Cannot be combined with video_url |
Can the prompt ask for a new camera angle?
You can write it, but the docs promise no outcome. They describe the prompt as the description of the edit and make no claim that scene, framing or subject are preserved across a new angle. Run a short test clip and look at the result before you edit footage you care about.
How do I run the edit?
Post to /v1/video-router/generate with an Idempotency-Key and "mode": "async", then poll the job. More prompt patterns are in video edit prompts, and the basic flow is in edit a video with a prompt.
Sources
Related posts
More in Models
- Invisible models in Pika vs Sume Auto echoing sume/auto
Pika hides model names unless you ask. Sume's model sume/auto also hides the family and echoes sume/auto; pin a catalog id when you need a known model.
- Pika Soundtrack: video in, sound out. What Sume has instead
Pika Soundtrack scores a finished video. Sume's docs offer generate_audio at video creation and a Timeline soundtrack bed, but no video-to-sound endpoint.
- 30-second video with sound: Pika Video Studio vs Sume ids
Pika Video Studio makes up to 30 seconds with sound. On Sume, seedance-2.5 and wan-3.0 reach 30 seconds; every other catalog model stops at 15.
- Pika Video Studio's 50 references vs Sume's per-model limits
Pika Video Studio attaches up to 50 references. Sume's caps are per model: 10 images and 3 short clips on Omni Flash, 1 to 8 images on Genjutsu.
Written by Sume