Veo 3.1 I2V
[Core Function] Veo 3.1 I2V is Google’s cinematic image-to-video generation model. [Strengths] It generates high-fidelity 4K video from a starting image. It supports advanced features like first-and-last frame conditioning and referencing up to three images. [Best For] Highly recommended for: animating concept art, creating cinematic transitions between images, and high-end video production. [Limitations] When using first+last frame or reference-only modes, the duration parameter must strictly be 8. Negative prompts are not supported in reference-only mode. [Routing] Use this model by default for high-quality image-to-video tasks or when multiple reference images are provided.
Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
- Option 1 — Image mode
- Option 2 — Reference mode
Veo 3.1 / Veo 3.1 Fast image-to-video request. Choose one option — image mode and referenceImages mode are mutually exclusive. Resolution up to 4K. Constraints verified 2026-04-29 against Google raw API, see each parameter for details.
Video description text guiding the animation
1"The character waves and smiles at the camera"
Starting frame. Accepts an image URL (e.g. https://example.com/frame.jpg).
"https://example.com/frame.jpg"
End frame. Accepts an image URL. Constraint: duration must be 8 when using this parameter.
"https://example.com/last-frame.jpg"
Text describing what to avoid in the generated video.
"blurry, low quality, distorted"
Video aspect ratio
16:9, 9:16 "16:9"
Video duration in seconds (string type). Constraint: When using lastFrame, must be 8 — values 4 or 6 will be rejected by Google. Otherwise 4, 6, 8 are all valid.
4, 6, 8 "8"
Video resolution. Constraint: 1080p and 4k are only available when duration is 8.
720p, 1080p, 4k "1080p"
Person generation policy
allow_adult "allow_adult"