Customize your input with more control.
Customize your input with more control.
Type # to reference inputs.
Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif, heic, heif
Customize your input with more control.
Your request will cost $0.2 per video.
Your request will cost $0.2 per video.
Ovi can generate videos with audio from image and text inputs.
https://fal.run/fal-ai/ovi/image-to-videofal-ai/ovi/image-to-videoFor more details, see fal.ai pricing.
This model can be used via our HTTP API or more conveniently via our client libraries. See the input and output schema below, as well as the usage examples.
The API accepts the following input parameters:
prompt (string, required):
The text prompt to guide video generation.
negative_prompt (string, optional):
Negative prompt for video generation. Default value: "jitter, bad hands, blur, distortion"
"jitter, bad hands, blur, distortion"num_inference_steps (integer, optional):
The number of inference steps. Default value: 30
301 to 50audio_negative_prompt (string, optional):
Negative prompt for audio generation. Default value: "robotic, muffled, echo, distorted"
"robotic, muffled, echo, distorted"seed (integer, optional):
Random seed for reproducibility. If None, a random seed is chosen.
image_url (string, required):
The image URL to guide video generation.
Required Parameters Example:
json{ "prompt": "An intimate close-up of a European woman with long dark hair as she gently brushes her hair in a softly lit bedroom, her delicate hand moving in the foreground. She looks directly into the camera with calm, focused eyes, a faint serene smile glowing in the warm lamp light. She says, <S>[soft whisper] I am an artificial intelligence.<E>.<AUDCAP>Soft whispering female voice, ASMR tone with gentle breaths, cozy room acoustics, subtle emphasis on \"I am an artificial intelligence\".<ENDAUDCAP>", "image_url": "https://storage.googleapis.com/falserverless/example_inputs/ovi_i2v_input.png" }
Full Example:
json{ "prompt": "An intimate close-up of a European woman with long dark hair as she gently brushes her hair in a softly lit bedroom, her delicate hand moving in the foreground. She looks directly into the camera with calm, focused eyes, a faint serene smile glowing in the warm lamp light. She says, <S>[soft whisper] I am an artificial intelligence.<E>.<AUDCAP>Soft whispering female voice, ASMR tone with gentle breaths, cozy room acoustics, subtle emphasis on \"I am an artificial intelligence\".<ENDAUDCAP>", "negative_prompt": "jitter, bad hands, blur, distortion", "num_inference_steps": 30, "audio_negative_prompt": "robotic, muffled, echo, distorted", "image_url": "https://storage.googleapis.com/falserverless/example_inputs/ovi_i2v_input.png" }
The API returns the following output format:
video (File, optional):
The generated video file.
seed (integer, required):
The seed used for generation.
Example Response:
json{ "video": { "url": "https://storage.googleapis.com/falserverless/example_inputs/ovi_i2v_output.mp4" } }
bashcurl --request POST \ --url https://fal.run/fal-ai/ovi/image-to-video \ --header "Authorization: Key $FAL_KEY" \ --header "Content-Type: application/json" \ --data '{ "prompt": "An intimate close-up of a European woman with long dark hair as she gently brushes her hair in a softly lit bedroom, her delicate hand moving in the foreground. She looks directly into the camera with calm, focused eyes, a faint serene smile glowing in the warm lamp light. She says, <S>[soft whisper] I am an artificial intelligence.<E>.<AUDCAP>Soft whispering female voice, ASMR tone with gentle breaths, cozy room acoustics, subtle emphasis on \"I am an artificial intelligence\".<ENDAUDCAP>", "image_url": "https://storage.googleapis.com/falserverless/example_inputs/ovi_i2v_input.png" }'
Ensure you have the Python client installed:
bashpip install fal-client
Then use the API client to make requests:
pythonimport fal_client def on_queue_update(update): if isinstance(update, fal_client.InProgress): for log in update.logs: print(log["message"]) result = fal_client.subscribe( "fal-ai/ovi/image-to-video", arguments={ "prompt": "An intimate close-up of a European woman with long dark hair as she gently brushes her hair in a softly lit bedroom, her delicate hand moving in the foreground. She looks directly into the camera with calm, focused eyes, a faint serene smile glowing in the warm lamp light. She says, <S>[soft whisper] I am an artificial intelligence.<E>.<AUDCAP>Soft whispering female voice, ASMR tone with gentle breaths, cozy room acoustics, subtle emphasis on \"I am an artificial intelligence\".<ENDAUDCAP>", "image_url": "https://storage.googleapis.com/falserverless/example_inputs/ovi_i2v_input.png" }, with_logs=True, on_queue_update=on_queue_update, ) print(result)
Ensure you have the JavaScript client installed:
bashnpm install --save @fal-ai/client
Then use the API client to make requests:
javascriptimport { fal } from "@fal-ai/client"; const result = await fal.subscribe("fal-ai/ovi/image-to-video", { input: { prompt: "An intimate close-up of a European woman with long dark hair as she gently brushes her hair in a softly lit bedroom, her delicate hand moving in the foreground. She looks directly into the camera with calm, focused eyes, a faint serene smile glowing in the warm lamp light. She says, <S>[soft whisper] I am an artificial intelligence.<E>.<AUDCAP>Soft whispering female voice, ASMR tone with gentle breaths, cozy room acoustics, subtle emphasis on \"I am an artificial intelligence\".<ENDAUDCAP>", image_url: "https://storage.googleapis.com/falserverless/example_inputs/ovi_i2v_input.png" }, logs: true, onQueueUpdate: (update) => { if (update.status === "IN_PROGRESS") { update.logs.map((log) => log.message).forEach(console.log); } }, }); console.log(result.data); console.log(result.requestId);