Fine-tune and integrate generative models into your APIs

Blueprint is the fastest way for developers to customize ML models. Start your project with pre-configured environments, GPUs, API endpoints, and instant deployment.

Get early access
Local model interface

Run generative models locally. No GPUs required.

baseten.models is a Python package that gives you full customizability over models like Stable Diffusion, Whisper, and FLAN-T5 from your local machine. Go beyond standard web API limitations to build the next generation of ML-powered applications.

Customize model objects

Gain complete control over today’s most exciting models—including the ability to interact and change model objects.

No GPU needed

Run models instantly and efficiently. Only pay per second for the predictions you run.

One-line installation

The baseten.models package comes with everything you need to run models locally—in one line of Python.

Get early access
🎨 Stable Diffusion
🎙 Whisper
📚 FLAN-T5
from baseten.models import StableDiffusionPipeline
from diffusers import LMSDiscreteScheduler 
lms = LMSDiscreteScheduler.from_config("runwayml/stable-diffusion-v1-5", subfolder="scheduler")

model = StableDiffusionPipeline(
     "runwayml/stable-diffusion-v1-5",
     scheduler=lms,
)

output = model(“man on moon”)
output[0][0].save(“./man-on-moon.jpeg”)
Fine-tuning

Easy-to-use dev tools, inspired by the latest in AI research.

There’s never been a more exciting time in machine learning than today. New, state of the art research is published daily. We’re translating these findings into easy-to-use developer tools to unlock new ways for developers to build with ML.

Fine tune text-to-image models

Quickly train text-to-image diffusion models on your own reference set to personalize outputs with a few lines of code.

Stable Diffusion x DreamBooth

Generate fully novel images in your preferred style with DreamBooth fine tuning on Stable Diffusion. See research.

Better large language models

Apply Chain-of-Thought prompting to improve complex reasoning for large language models. See research.

Tell us—what’s next?

Found ML research you want to build with? Reach out to us at support@baseten.co.

Get early access
Web IDE

Build & ship ML apps from one web IDE.

Start building with ML in seconds with our comprehensive web IDE. Add backends with Python functions, generate API routes instantly, and deploy automatically as changes are made.

Web IDE

Blueprint’s web IDE has everything you need to build with ML. Start coding in seconds, no set-up required.

API Routes

Define Python functions to build robust API routes. Test as you go with built-in testing tools and logs.

Automatic deployments

Changes to your model code and routes are deployed automatically and without incident.

Fully managed

Spend zero time on servers and infra. We host and manage your models and API routes for you.

Get early access
app.baseten.co/blueprint/your_project
Launching soon

Fine-tune and integrate generative models into your APIs

Blueprint is the fastest way for developers to interact with ML models. Start your project with pre-configured environments, GPUs, API endpoints, and instant deployment.

Get early access