Inference Providers documentation
Fal
Fal
All supported Fal models can be found here
fal is the generative media inference platform: call 1,000+ models by API, or deploy your own models, pipelines and apps on fal’s autoscaling GPUs with fal Serverless. Serverless deployments scale from zero to thousands of runners and back, are billed per second of runner lifetime (pricing), and can be deployed from a Python fal.App, a custom Docker container, or an existing HTTP server.
Founded in 2021 by Burkay Gur and Gorkem Yurtseven, fal.ai was born out of a shared passion for AI and a desire to address the challenges in AI infrastructure observed during their tenures at Coinbase and Amazon.
Supported tasks
Automatic Speech Recognition
Find out more about Automatic Speech Recognition here.
Language
Client
Provider
import os
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="fal-ai",
api_key=os.environ["HF_TOKEN"],
)
output = client.automatic_speech_recognition("sample1.flac", model="openai/whisper-large-v3")Image Segmentation
Find out more about Image Segmentation here.
Language
Client
Provider
import os
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="fal-ai",
api_key=os.environ["HF_TOKEN"],
)
output = client.image_segmentation("cats.jpg", model="briaai/RMBG-2.0")Image To Image
Find out more about Image To Image here.
Language
Client
Provider
import os
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="fal-ai",
api_key=os.environ["HF_TOKEN"],
)
with open("cat.png", "rb") as image_file:
input_image = image_file.read()
# output is a PIL.Image object
image = client.image_to_image(
input_image,
prompt="Turn the cat into a tiger.",
model="black-forest-labs/FLUX.2-klein-9B",
)Text To Image
Find out more about Text To Image here.
Language
Client
Provider
import os
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="fal-ai",
api_key=os.environ["HF_TOKEN"],
)
# output is a PIL.Image object
image = client.text_to_image(
"Astronaut riding a horse",
model="krea/Krea-2-Turbo",
)Text To Video
Find out more about Text To Video here.
Language
Provider
import os
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="fal-ai",
api_key=os.environ["HF_TOKEN"],
)
video = client.text_to_video(
"A young man walking on the street",
model="Wan-AI/Wan2.1-T2V-1.3B",
)