Inference Providers documentation

Replicate

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Replicate

Replicate is building tools so all software engineers can use AI as if it were normal software. You should be able to import an image generator the same way you import an npm package. You should be able to customize a model as easily as you can fork something on GitHub.

Supported tasks

Text To Image

Find out more about Text To Image here.

from huggingface_hub import InferenceClient

client = InferenceClient(
    provider="replicate",
    api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxx",
)

# output is a PIL.Image object
image = client.text_to_image(
    "Astronaut riding a horse",
    model="black-forest-labs/FLUX.1-dev",
)

Text To Video

Find out more about Text To Video here.

from huggingface_hub import InferenceClient

client = InferenceClient(
    provider="replicate",
    api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxx",
)

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