Text to Video

Generate an video based on a given text prompt.

For more details about the text-to-video task, check out its dedicated page! You will find examples and related materials.

Recommended models

tencent/HunyuanVideo: A strong model for consistent video generation.
Lightricks/LTX-Video: A text-to-video model with high fidelity motion and strong prompt adherence.
Wan-AI/Wan2.1-T2V-1.3B: A robust model for video generation.

Explore all available models and find the one that suits you best here.

Using the API

Language

Provider

Settings

from huggingface_hub import InferenceClient

client = InferenceClient(
    provider="fal-ai",
    api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxx",
)

video = client.text_to_video(
    "A young man walking on the street",
    model="Wan-AI/Wan2.1-T2V-14B",
)

API specification

Request

Payload
inputs*	string	The input text data (sometimes called “prompt”)
parameters	object
num_frames	number	The num_frames parameter determines how many video frames are generated.
guidance_scale	number	A higher guidance scale value encourages the model to generate videos closely linked to the text prompt, but values too high may cause saturation and other artifacts.
negative_prompt	string[]	One or several prompt to guide what NOT to include in video generation.
num_inference_steps	integer	The number of denoising steps. More denoising steps usually lead to a higher quality video at the expense of slower inference.
seed	integer	Seed for the random number generator.

Some options can be configured by passing headers to the Inference API. Here are the available headers:

Headers
authorization	string	Authentication header in the form `'Bearer: hf_**'` when `hf_**` is a personal user access token with Inference API permission. You can generate one from your settings page.
x-use-cache	boolean, default to `true`	There is a cache layer on the inference API to speed up requests we have already seen. Most models can use those results as they are deterministic (meaning the outputs will be the same anyway). However, if you use a nondeterministic model, you can set this parameter to prevent the caching mechanism from being used, resulting in a real new query. Read more about caching here.
x-wait-for-model	boolean, default to `false`	If the model is not ready, wait for it instead of receiving 503. It limits the number of requests required to get your inference done. It is advised to only set this flag to true after receiving a 503 error, as it will limit hanging in your application to known places. Read more about model availability here.

For more information about Inference API headers, check out the parameters guide.

Response

Body
video	unknown	The generated video returned as raw bytes in the payload.