Add JavaScript quickstart, link to all Replicate models, and billing section
Browse files
README.md
CHANGED
|
@@ -9,13 +9,15 @@ pinned: false
|
|
| 9 |
|
| 10 |
# Run AI with an API
|
| 11 |
|
| 12 |
-
Replicate lets developers run, fine-tune, and deploy open models with a production-ready API. On Hugging Face, you can use Replicate as an Inference Provider for popular models across image generation, video generation, speech, and
|
| 13 |
|
| 14 |
-
**
|
|
|
|
|
|
|
| 15 |
|
| 16 |
**Read the integration docs:** [Replicate on Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers/providers/replicate)
|
| 17 |
|
| 18 |
-
**
|
| 19 |
|
| 20 |
## Why use Replicate on Hugging Face?
|
| 21 |
|
|
@@ -23,7 +25,9 @@ Use Replicate infrastructure through Hugging Face's standard Inference Providers
|
|
| 23 |
|
| 24 |
## Get started in 30 seconds
|
| 25 |
|
| 26 |
-
|
|
|
|
|
|
|
| 27 |
|
| 28 |
```bash
|
| 29 |
pip install huggingface_hub pillow
|
|
@@ -47,4 +51,40 @@ image = client.text_to_image(
|
|
| 47 |
image.save("replicate-astronaut.png")
|
| 48 |
```
|
| 49 |
|
| 50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
# Run AI with an API
|
| 11 |
|
| 12 |
+
Replicate lets developers run, fine-tune, and deploy open models with a production-ready API. On Hugging Face, you can use Replicate as an Inference Provider for popular models across image generation, image editing, video generation, speech recognition, and text-to-speech.
|
| 13 |
|
| 14 |
+
**Featured models:** [Run with Replicate](https://huggingface.co/collections/replicate/run-with-replicate-6a04d0792d027edbf66c7155)
|
| 15 |
+
|
| 16 |
+
**All Replicate-powered models:** [Browse the full list](https://huggingface.co/models?inference_provider=replicate&sort=trending)
|
| 17 |
|
| 18 |
**Read the integration docs:** [Replicate on Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers/providers/replicate)
|
| 19 |
|
| 20 |
+
**Examples for every task:** [Replicate Inference Provider Examples](https://huggingface.co/spaces/replicate/inference-provider-examples)
|
| 21 |
|
| 22 |
## Why use Replicate on Hugging Face?
|
| 23 |
|
|
|
|
| 25 |
|
| 26 |
## Get started in 30 seconds
|
| 27 |
|
| 28 |
+
Create a token at [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens) with the "Make calls to Inference Providers" permission, then generate an image:
|
| 29 |
+
|
| 30 |
+
**Python**
|
| 31 |
|
| 32 |
```bash
|
| 33 |
pip install huggingface_hub pillow
|
|
|
|
| 51 |
image.save("replicate-astronaut.png")
|
| 52 |
```
|
| 53 |
|
| 54 |
+
**JavaScript**
|
| 55 |
+
|
| 56 |
+
```bash
|
| 57 |
+
npm install @huggingface/inference
|
| 58 |
+
export HF_TOKEN=hf_...
|
| 59 |
+
```
|
| 60 |
+
|
| 61 |
+
```js
|
| 62 |
+
import { InferenceClient } from "@huggingface/inference";
|
| 63 |
+
import { writeFile } from "node:fs/promises";
|
| 64 |
+
|
| 65 |
+
const client = new InferenceClient(process.env.HF_TOKEN);
|
| 66 |
+
|
| 67 |
+
const image = await client.textToImage({
|
| 68 |
+
provider: "replicate",
|
| 69 |
+
model: "Tongyi-MAI/Z-Image-Turbo",
|
| 70 |
+
inputs: "A cinematic photo of an astronaut riding a horse",
|
| 71 |
+
});
|
| 72 |
+
|
| 73 |
+
const ext = image.type.split("/")[1];
|
| 74 |
+
await writeFile(`replicate-astronaut.${ext}`, Buffer.from(await image.arrayBuffer()));
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
+
For cURL and task-specific examples, see the [Replicate provider docs](https://huggingface.co/docs/inference-providers/providers/replicate).
|
| 78 |
+
|
| 79 |
+
## Billing
|
| 80 |
+
|
| 81 |
+
You have two options:
|
| 82 |
+
|
| 83 |
+
- **Bill through Hugging Face (default):** requests are charged to your Hugging Face account at Replicate's rates with no markup, and your monthly HF credits apply. No Replicate account needed.
|
| 84 |
+
- **Use your own Replicate key:** add your Replicate API token in your [Inference Providers settings](https://huggingface.co/settings/inference-providers). Your code stays the same, and usage is billed directly by Replicate.
|
| 85 |
+
|
| 86 |
+
Team and Enterprise orgs can bill usage to the organization with `bill_to="your-org"` (Python) or `{ billTo: "your-org" }` (JavaScript). See [Pricing and Billing](https://huggingface.co/docs/inference-providers/pricing) for details.
|
| 87 |
+
|
| 88 |
+
## Go further on Replicate
|
| 89 |
+
|
| 90 |
+
Need fine-tuning, deployments, or thousands more models? Visit [replicate.com](https://replicate.com) and the [Replicate docs](https://replicate.com/docs).
|