Replicate Python client

This is a Python client for Replicate. It lets you run models from your Python code or Jupyter notebook, and do various other things on Replicate.

You can run a model and get its output:

>>> import replicate

>>> model = replicate.models.get("replicate/hello-world")
>>> model.predict(text="python")
"hello python"

>>> model = replicate.models.get("replicate/resnet")
>>> model.predict(image=open("mystery.jpg", "rb"))
[['n02123597', 'Siamese_cat', 0.8829364776611328],
 ['n02123394', 'Persian_cat', 0.09810526669025421],
 ['n02123045', 'tabby', 0.005758069921284914]]

You can run a model and feed the output into another model:

>>> image = replicate.models.get("afiaka87/laionide-v4").predict(prompt="avocado armchair")
>>> upscaled_image = replicate.models.get("jingyunliang/swinir").predict(image=image)

Run a model and get its output while it's running:

model = replicate.models.get("pixray/text2image")
for image in model.predict(prompt="san francisco sunset"):
    display(image)

You can start a model and run it in the background:

>>> model = replicate.models.get("kvfrans/clipdraw")
>>> prediction = replicate.predictions.create(
...    version=model.versions.list()[0],
...    input={"prompt":"Watercolor painting of an underwater submarine"})

>>> prediction
Prediction(...)

>>> prediction.status
'starting'

>>> dict(prediction)
{"id": "...", "status": "starting", ...}

>>> prediction.reload()
>>> prediction.status
'processing'

>>> print(prediction.logs)
iteration: 0, render:loss: -0.6171875
iteration: 10, render:loss: -0.92236328125
iteration: 20, render:loss: -1.197265625
iteration: 30, render:loss: -1.3994140625

>>> prediction.wait()

>>> prediction.status
'succeeded'

>>> prediction.output
'https://.../output.png'

You can list all the predictions you've run:

>>> replicate.predictions.list()
[<Prediction: 8b0ba5ab4d85>, <Prediction: 494900564e8c>]

Install

pip install replicate

Authentication

Set the REPLICATE_API_TOKEN environment variable to your API token. For example, run this before running any Python scripts that use the API:

export REPLICATE_API_TOKEN=<your token>

We recommend not adding it directly to your source code, because you don't want to put your API in source control. If anyone uses your API key, their usage would be charged to your account.

Development

See CONTRIBUTING.md

Release files for replicate 0.0.1a10

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for replicate 0.0.1a10
File	Size	Uploaded
replicate-0.0.1a10.tar.gz	11.1 kB	May 27, 2022	Details

Release files / replicate-0.0.1a10.tar.gz

Download URL	replicate-0.0.1a10.tar.gz
Size	11.1 kB
Tags	Source
SHA-256 checksum How to use checksums	`a850a0b7050e28d0fca5435f3af13514f4a1cccea7cb6aac0563aac7d1d8e9bc`
BLAKE2b-256 checksum How to use checksums	`ee9d648298217dd6f498484b222efb455464be6a1c904bf01e2bc2f61bd8803e`
Upload date	May 27, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.0 CPython/3.9.13`