How to deploy Stable Diffusion 3.5 Large on Modal

All posts

Back

Model Library

December 16, 2024•5 minute read

Yiren Lu@YirenLu

Solutions Engineer

Introduction to Stable Diffusion 3.5 Large

Stable Diffusion 3.5 Large is the most powerful model in the Stable Diffusion family. This model is ideal for professional use cases. Our example code shows how to run a distilled version, Stable Diffusion 3.5 Large Turbo, which generates high-quality images with exceptional prompt adherence in just 4 steps, making it considerably faster than Stable Diffusion 3.5 Large.

To run the following code, you will need to:

Create an account at modal.com
Run pip install modal to install the modal Python package
Run modal setup to authenticate (if this doesn’t work, try python -m modal setup)
Copy the code below into a file called app.py
Run modal run app.py

Please note that this code does not come with a UI. For a more detailed example of how to run Stable Diffusion 3.5 Large Turbo as a CLI, API, and UI, refer here.

import io
import random
from pathlib import Path

import modal

app = modal.App("stable-diffusion-large-model-library")

image = (
    modal.Image.debian_slim(python_version="3.12")
    .pip_install(
        "accelerate==0.33.0",
        "diffusers==0.31.0",
        "fastapi[standard]==0.115.4",
        "huggingface-hub[hf_transfer]==0.25.2",
        "sentencepiece==0.2.0",
        "torch==2.5.1",
        "torchvision==0.20.1",
        "transformers~=4.44.0",
    )
    .env({"HF_HUB_ENABLE_HF_TRANSFER": "1"})
)

with image.imports():
    import diffusers
    import torch


@app.cls(
    image=image,
    gpu="H100",
    timeout=600,
)
class Inference:
    @modal.build()
    @modal.enter()
    def initialize(self):
        self.pipe = diffusers.StableDiffusion3Pipeline.from_pretrained(
            "adamo1139/stable-diffusion-3.5-large-turbo-ungated",
            revision="9ad870ac0b0e5e48ced156bb02f85d324b7275d2",
            torch_dtype=torch.bfloat16,
        )

    @modal.enter()
    def move_to_gpu(self):
        self.pipe.to("cuda")

    @modal.method()
    def run(self, prompt: str, batch_size: int = 4, seed: int = None) -> list[bytes]:
        seed = seed if seed is not None else random.randint(0, 2**32 - 1)
        print("seeding RNG with", seed)
        torch.manual_seed(seed)

        images = self.pipe(
            prompt,
            num_images_per_prompt=batch_size,
            num_inference_steps=4,
            guidance_scale=0.0,
            max_sequence_length=512,
        ).images

        image_output = []
        for image in images:
            with io.BytesIO() as buf:
                image.save(buf, format="PNG")
                image_output.append(buf.getvalue())
        torch.cuda.empty_cache()
        return image_output


@app.local_entrypoint()
def main(prompt: str = "A princess riding on a pony"):
    output_dir = Path("/tmp/stable-diffusion")
    output_dir.mkdir(exist_ok=True)

    images = Inference().run.remote(prompt, batch_size=1)

    for i, image_bytes in enumerate(images):
        output_path = output_dir / f"output_{i:02d}.png"
        output_path.write_bytes(image_bytes)
        print(f"Saved {output_path}")

Introduction to Stable Diffusion 3.5 Large

Example code for running Stable Diffusion 3.5 Large on Modal

Ship your first app in minutes.