Add Replicate quickstart

README.md

@@ -21,7 +21,14 @@ Replicate lets developers run, fine-tune, and deploy open models with a producti
 
 Use Replicate infrastructure through Hugging Face's standard Inference Providers interface. You can call image, video, speech, and audio models with the same `InferenceClient`, your existing `HF_TOKEN`, and a provider switch instead of wiring up a separate integration path.
 
-## Get started
+## Get started in 30 seconds
+
+Install the Hub client, set your token, generate an image, and save it locally:
+
+```bash
+pip install huggingface_hub pillow
+export HF_TOKEN=hf_...
+```
 
 ```python
 import os
@@ -36,3 +43,8 @@ image = client.text_to_image(
     "A cinematic photo of an astronaut riding a horse",
     model="Tongyi-MAI/Z-Image-Turbo",
 )
+
+image.save("replicate-astronaut.png")
+```
+
+For JavaScript, cURL, and task-specific examples, see the [Replicate provider docs](https://huggingface.co/docs/inference-providers/providers/replicate).