Gemini Omni 1.2 Flash Image to Video API
Animate a still image into a 15-second video with audio.
POST /v2/gemini-omni-1.2-flash-image-to-video · submit + poll 1# pip install "segmind>=1.1.0"
2# export SEGMIND_API_KEY="YOUR_API_KEY"
3from segmind import SegmindClient, InferenceFailed, InferenceTimeout
4
5# Async (v2) — recommended for long-running / video models.
6# run() blocks up to 600s; submit_async + job.wait(timeout=...) sets a longer
7# deadline and keeps the request_id so you can re-poll later.
8client = SegmindClient() # reads SEGMIND_API_KEY
9payload = {
10 "first_frame_image": "https://segmind-resources.s3.amazonaws.com/input/gemini-omni-1.2-flash-image-to-video-firstframe.jpg",
11 "prompt": "Locked-off camera, nothing in the background moves. The three blue bars grow upward one after another into tall columns of different heights - first the 'JAN' bar to a short height, then the 'MAY' bar to a medium height, then the 'SEP' bar to the tallest. After the bars finish growing, a yellow rounded tag slides in at the top-right reading 'MM PER MONTH'. The deep teal background, the faint grid and the 'CITY RAINFALL' title stay perfectly still; only the bars and the tag move. Flat 2D vector style, no people, no photorealism. Sound: a short rising marimba note as each bar grows, then a light chime when the tag appears. Every word spelled exactly as given, no other text.",
12 "duration": 5,
13 "resolution": "720p",
14 "aspect_ratio": "16:9",
15}
16job = client.submit_async("gemini-omni-1.2-flash-image-to-video", **payload)
17print(job.request_id) # available immediately
18try:
19 result = job.wait(timeout=900, interval=2.0)
20 print(result["status"]) # COMPLETED
21 print(result.get("output")) # model output (e.g. video URL)
22except InferenceTimeout as e:
23 print("still running:", e.request_id) # re-poll later with this id
24except InferenceFailed as e:
25 print("failed:", e.detail)
26
27# Fast models (<=600s) can use the one-liner instead:
28# result = segmind.run("gemini-omni-1.2-flash-image-to-video", **payload) 1# pip install "segmind>=1.1.0"
2# export SEGMIND_API_KEY="YOUR_API_KEY"
3from segmind import SegmindClient, InferenceFailed, InferenceTimeout
4
5# Async (v2) — recommended for long-running / video models.
6# run() blocks up to 600s; submit_async + job.wait(timeout=...) sets a longer
7# deadline and keeps the request_id so you can re-poll later.
8client = SegmindClient() # reads SEGMIND_API_KEY
9payload = {
10 "first_frame_image": "https://segmind-resources.s3.amazonaws.com/input/gemini-omni-1.2-flash-image-to-video-firstframe.jpg",
11 "prompt": "Locked-off camera, nothing in the background moves. The three blue bars grow upward one after another into tall columns of different heights - first the 'JAN' bar to a short height, then the 'MAY' bar to a medium height, then the 'SEP' bar to the tallest. After the bars finish growing, a yellow rounded tag slides in at the top-right reading 'MM PER MONTH'. The deep teal background, the faint grid and the 'CITY RAINFALL' title stay perfectly still; only the bars and the tag move. Flat 2D vector style, no people, no photorealism. Sound: a short rising marimba note as each bar grows, then a light chime when the tag appears. Every word spelled exactly as given, no other text.",
12 "duration": 5,
13 "resolution": "720p",
14 "aspect_ratio": "16:9",
15}
16job = client.submit_async("gemini-omni-1.2-flash-image-to-video", **payload)
17print(job.request_id) # available immediately
18try:
19 result = job.wait(timeout=900, interval=2.0)
20 print(result["status"]) # COMPLETED
21 print(result.get("output")) # model output (e.g. video URL)
22except InferenceTimeout as e:
23 print("still running:", e.request_id) # re-poll later with this id
24except InferenceFailed as e:
25 print("failed:", e.detail)
26
27# Fast models (<=600s) can use the one-liner instead:
28# result = segmind.run("gemini-omni-1.2-flash-image-to-video", **payload)API Endpoint
https://api.segmind.com/v1/gemini-omni-1.2-flash-image-to-videoParameters
first_frame_imagerequiredstring (uri)The still the clip starts from (JPG or PNG). Use a crisp, well-composed frame.
"https://segmind-resources.s3.amazonaws.com/input/gemini-omni-1.2-flash-image-to-video-firstframe.jpg"promptrequiredstringDescribe the motion, camera and sound. List beats in order and quote on-screen text exactly.
"Locked-off camera, nothing in the background moves. The three blue bars grow upward one after another into tall columns of different heights - first the 'JAN' bar to a short height, then the 'MAY' bar to a medium height, then the 'SEP' bar to the tallest. After the bars finish growing, a yellow rounded tag slides in at the top-right reading 'MM PER MONTH'. The deep teal background, the faint grid and the 'CITY RAINFALL' title stay perfectly still; only the bars and the tag move. Flat 2D vector style, no people, no photorealism. Sound: a short rising marimba note as each bar grows, then a light chime when the tag appears. Every word spelled exactly as given, no other text."aspect_ratiooptionalstring16:9 landscape or 9:16 vertical. Choose 9:16 for mobile and social.
"16:9""16:9""9:16"durationoptionalintegerClip length in seconds, 3 to 15. Keep it short for drafts, longer for full scenes.
5Range: 3 - 15last_frame_imageoptionalstring (uri)Optional ending frame; with both frames the clip caps at 10 seconds. Add it when the ending matters.
resolutionoptionalstringOutput resolution: 360p, 720p, 1080p or 4k. Draft at 360p, raise for finals.
"720p""360p""720p""1080p""4k"seedoptionalintegerRandom seed; -1 randomizes. Set a fixed number to reproduce a result.
-1Response Type
Returns: Video
Asynchronous requests (v2)
Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.
- 1
POST /v2/gemini-omni-1.2-flash-image-to-videoSubmit — returns request_id, status_url, response_url
- 2
GET /v2/requests/{id}/statusPoll — until COMPLETED or FAILED
- 3
GET /v2/requests/{id}Result — final response body
Status states
- A FAILED request is served as HTTP 422 — the body still carries the error detail.
- An unknown or expired request_id returns HTTP 404.
- Results are retained for 1 hour, then expire.
- Content / RAI blocks surface as FAILED, not a separate state.
- Track completion by polling the status endpoint.
Common Error Codes
The API returns standard HTTP status codes. Detailed error messages are provided in the response body.
Bad Request
Invalid parameters or request format
Unauthorized
Missing or invalid API key
Forbidden
Insufficient permissions
Not Found
Model or endpoint not found
Insufficient Credits
Not enough credits to process request
Rate Limited
Too many requests
Server Error
Internal server error
Bad Gateway
Service temporarily unavailable
Timeout
Request timed out