Price a generation

Output aspect ratio

URL of an audio file (voice or music) the video syncs to

Video editing: auto generates new audio, origin keeps the input video's audio

Whether the background is transparent or opaque

Optional https URL, up to 2048 characters. When the job is final, completed with its outputs or failed or canceled with its error, it is POSTed there once, as JSON: the body GET /api/v2/generations/{id} answers. A network error, a 5xx or a 429 is retried for about six minutes; any other answer ends it. Nothing signs the request, so read the job back with GET before trusting what it says

Keep the camera position fixed

Character orientation source for motion control

Video duration in seconds

Batch mode: generate a set of related images (up to 12)

Rewrite the prompt in more detail before generating, with the model's prompting guide or its own built-in rewriter (GET /api/v2/models/{id} says which); free, included in the generation price

URL of a video clip to continue (image-to-video mode); use instead of image and last_image

Frames per second

Generate a soundtrack for the video

Use faster generation mode

Enable Google Search grounding for image generation

Guidance scale (CFG scale)

Guidance scale (CFG scale)

Output height in pixels

Use high performance mode (better quality)

Any string you choose, up to 255 characters. A create repeated with the same key (after a timeout, say) returns the first job, marked idempotent_replay: true, instead of starting and charging a second; while the first is still being submitted the repeat answers 409 idempotency_in_progress. A different request under a used key answers 422 idempotency_key_reused, so use a new key for a new request

Input image URL: the image to edit, animate or work on

Number of denoising steps

Input image URL

Use Pro variant

URL of the image the video ends on; pair with image, which it starts on

LoRA scale factor

How strongly the transformer LoRA is applied

How strongly the second transformer LoRA is applied

LoRA weights URL or identifier

URL of LoRA weights (.safetensors) for the transformer

URL of a second set of LoRA weights (.safetensors) for the transformer

Most images to make; state the same number in the prompt. The model may make fewer, and images not delivered are refunded

Approximate output size in megapixels

Model id from GET /api/v2/models

Number of images, billed per image: 1-4, or 1-12 with enable_sequential. 1 when omitted. Images not delivered are refunded

Negative prompt to avoid certain content

Clip length in frames: the clip lasts num_frames / fps seconds. 121 when omitted (5 s at 24 fps), or 81 with high_performance (3.4 s)

Number of denoising steps

Number of layers to split the image into, 2 to 8 (billed per layer)

Number of images to generate, billed per image; images not delivered are refunded

The model's own option: it translates the prompt to Chinese before generating. Independent of translate_prompt, which translates the prompt to English before the model gets it; one of the two is enough for a prompt in another language

Output image format

Output quality (1-100)

The prompt to generate from

Let the model expand the prompt before generating

Strength of prompt influence for image-to-image

Quality level: basic (2K) or high (4K)

Output resolution

Shifts the denoising schedule: higher values favour overall composition and motion, lower values fine detail

Random seed for reproducibility; 0 or omitted picks one at random

Output size preset

Reason about the prompt before generating; text-to-image without enable_sequential only

Translate the prompt to English before generating; free, included in the generation price

How the images in veo31_image_urls are used. Leave it out and the count decides: no images is TEXT_2_VIDEO, one or two are the first and last frames (FIRST_AND_LAST_FRAMES_2_VIDEO), three are reference images (REFERENCE_2_VIDEO, which takes veo3_fast and 16:9 only)

Quality tier: veo3 renders at higher quality, veo3_fast renders faster and costs less

Watermark text to put on the video

Clip length in frames: the clip lasts video_length / fps seconds, 129 frames at 24 fps (5.4 s) by default

Add a watermark to the output

Let the model look up the prompt's subject on the web; text-to-video only

Output width in pixels

Whether balance covers cost

Your credits now

Credits missing to cover cost; 0 when affordable