infery
← All models

Bernini-R Text to Video

bernini-r-text-to-video

Video generationby Bernini R

Generate high-quality video from a text prompt with Bernini-R, ByteDance's unified video generation and editing model.

Example

Details

Accepts
text

Pricing

Price
10 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedSeed for reproducibility. Random when omitted.
promptrequiredstringText prompt or editing instruction.
num_framesintegerNumber of frames. Snapped internally to 4k+1.
accelerationstringenum: none, regularAcceleration level. 'regular' enables MagCache step-skipping for faster generation at a small quality cost; 'none' (default) runs the full denoising schedule.
aspect_ratiostringenum: 16:9, 9:16, 1:1Output aspect ratio.
max_image_sizeintegerLong-edge size (px). Sets the output size for generation tasks and caps source/reference media for editing tasks.
negative_promptNegative prompt. Defaults to the standard Wan2.2 negative prompt.
frames_per_secondintegerOutput frames per second.
num_inference_stepsintegerNumber of denoising steps.
enable_prompt_expansionbooleanRewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts; off by default.

Output

FieldTypeDescription
seedintegerSeed used for generation.
videoGenerated / edited video.
actual_promptThe final prompt after expansion (set only when prompt expansion ran).