Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
166 changes: 89 additions & 77 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,44 +1,66 @@
# 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.
This is a Python client for [Replicate](https://replicate.com). It lets you run models from your Python code or Jupyter notebook, and do various other things on Replicate.

Grab your token from [replicate.com/account](https://replicate.com/account) and authenticate by setting it as an environment variable:
## Install

```sh
pip install replicate
```

## Authenticate

Before running any Python scripts that use the API, you need to set your Replicate API token in your environment.

Grab your token from [replicate.com/account](https://replicate.com/account) and set it as an environment variable:

```
export REPLICATE_API_TOKEN=[token]
export REPLICATE_API_TOKEN=<your token>
```

You can run a model and get its output:
We recommend not adding the token directly to your source code, because you don't want to put your credentials in source control. If anyone used your API key, their usage would be charged to your account.

## Run a model

Create a new Python file and add the following code:

```python
$ python
>>> import replicate
>>> model = replicate.models.get("stability-ai/stable-diffusion")
>>> version = model.versions.get("27b93a2413e7f36cd83da926f3656280b2931564ff050bf9575f1fdf9bcd7478")
>>> version.predict(prompt="a 19th century portrait of a wombat gentleman")
['https://replicate.com/api/models/stability-ai/stable-diffusion/files/50fcac81-865d-499e-81ac-49de0cb79264/out-0.png']
import replicate
model = replicate.models.get("stability-ai/stable-diffusion")
version = model.versions.get("27b93a2413e7f36cd83da926f3656280b2931564ff050bf9575f1fdf9bcd7478")
version.predict(prompt="a 19th century portrait of a wombat gentleman")

# ['https://replicate.com/api/models/stability-ai/stable-diffusion/files/50fcac81-865d-499e-81ac-49de0cb79264/out-0.png']
```

Some models, like [replicate/resnet](/replicate/resnet), receive images as inputs. To pass a file as an input, use a file handle or URL
Some models, like [methexis-inc/img2prompt](https://replicate.com/methexis-inc/img2prompt), receive images as inputs. To pass a file as an input, use a file handle or URL:

```python
>>> model = replicate.models.get("replicate/resnet")
>>> version = model.versions.get("dd782a3d531b61af491d1026434392e8afb40bfb53b8af35f727e80661489767")
>>> version.predict(image=open("mystery.jpg", "rb"))
[['n02123597', 'Siamese_cat', 0.8829364776611328],
['n02123394', 'Persian_cat', 0.09810526669025421],
['n02123045', 'tabby', 0.005758069921284914]]
model = replicate.models.get("methexis-inc/img2prompt")
version = model.versions.get("50adaf2d3ad20a6f911a8a9e3ccf777b263b8596fbd2c8fc26e8888f8a0edbb5")
inputs = {
"image": open("path/to/mystery.jpg", "rb"),
}
output = version.predict(**inputs)

# [['n02123597', 'Siamese_cat', 0.8829364776611328],
# ['n02123394', 'Persian_cat', 0.09810526669025421],
# ['n02123045', 'tabby', 0.005758069921284914]]
```

## Compose models into a pipeline

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

```python
>>> laionide = replicate.models.get("afiaka87/laionide-v4").versions.get("b21cbe271e65c1718f2999b038c18b45e21e4fba961181fbfae9342fc53b9e05")
>>> swinir = replicate.models.get("jingyunliang/swinir").versions.get("660d922d33153019e8c263a3bba265de882e7f4f70396546b6c9c8f9d47a021a")
>>> image = laionide.predict(prompt="avocado armchair")
>>> upscaled_image = swinir.predict(image=image)
laionide = replicate.models.get("afiaka87/laionide-v4").versions.get("b21cbe271e65c1718f2999b038c18b45e21e4fba961181fbfae9342fc53b9e05")
swinir = replicate.models.get("jingyunliang/swinir").versions.get("660d922d33153019e8c263a3bba265de882e7f4f70396546b6c9c8f9d47a021a")
image = laionide.predict(prompt="avocado armchair")
upscaled_image = swinir.predict(image=image)
```

## Get output from a running model

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

```python
Expand All @@ -48,69 +70,77 @@ for image in version.predict(prompts="san francisco sunset"):
display(image)
```

## Run a model in the background

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

```python
>>> model = replicate.models.get("kvfrans/clipdraw")
>>> version = model.versions.get("5797a99edc939ea0e9242d5e8c9cb3bc7d125b1eac21bda852e5cb79ede2cd9b")
>>> prediction = replicate.predictions.create(
... version=version,
... input={"prompt":"Watercolor painting of an underwater submarine"})
model = replicate.models.get("kvfrans/clipdraw")
version = model.versions.get("5797a99edc939ea0e9242d5e8c9cb3bc7d125b1eac21bda852e5cb79ede2cd9b")
prediction = replicate.predictions.create(
version=version,
input={"prompt":"Watercolor painting of an underwater submarine"})

>>> prediction
Prediction(...)
# >>> prediction
# Prediction(...)

>>> prediction.status
'starting'
# >>> prediction.status
# 'starting'

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

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

>>> prediction.status
'succeeded'
# >>> prediction.status
# 'succeeded'

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

## Cancel a prediction

You can cancel a running prediction:

```python
>>> model = replicate.models.get("kvfrans/clipdraw")
>>> version = model.versions.get("5797a99edc939ea0e9242d5e8c9cb3bc7d125b1eac21bda852e5cb79ede2cd9b")
>>> prediction = replicate.predictions.create(
... version=version,
... input={"prompt":"Watercolor painting of an underwater submarine"})
model = replicate.models.get("kvfrans/clipdraw")
version = model.versions.get("5797a99edc939ea0e9242d5e8c9cb3bc7d125b1eac21bda852e5cb79ede2cd9b")
prediction = replicate.predictions.create(
version=version,
input={"prompt":"Watercolor painting of an underwater submarine"})

>>> prediction.status
'starting'
# >>> prediction.status
# 'starting'

>>> prediction.cancel()
# >>> prediction.cancel()

>>> prediction.reload()
>>> prediction.status
'canceled'
# >>> prediction.reload()
# >>> prediction.status
# 'canceled'
```

## List predictions

You can list all the predictions you've run:

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

## Load output files

Output files are returned as HTTPS URLs. You can load an output file as a buffer:

```python
Expand All @@ -124,24 +154,6 @@ urlretrieve(out[0], "/tmp/out.png")
background = Image.open("/tmp/out.png")
```

## Install

```sh
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.

If you have access to the API, [you can find your API key on your dashboard when signed in](https://replicate.com).

## Development

See [CONTRIBUTING.md](CONTRIBUTING.md)