Qwen-Image-Edit-Plus

This guide walks you through deploying the Pruna-optimized Qwen-Image-Edit-Plus model.

What are the prerequisites?

To run the model, you’ll need:

• HuggingFace token (HF_TOKEN): Enables you to download the optimized model.

• Pruna token (PRUNA_TOKEN): Enables you to load and run the model.

• An environment with pruna_pro installed: pip install pruna_pro==0.2.9

What inputs does the model support?

• prompt: Input text to generate video from.

• image: List of images in PIL format to be edited

• seed: Random seed. Leave blank for random

• go_fast: We offer a very fast and a conservative option.

How do I load the model?

You can initialize the Pruna-optimized Qwen-Image-Edit-Plus model directly with PrunaProModel.from_pretrained:

from pruna_pro import PrunaProModel

self.pipe = PrunaProModel.from_pretrained(
            "PrunaAI/Qwen-Image-Edit-Plus",
            token="HF_TOKEN",
            hf_token="PRUNA_TOKEN"
        )

What does a minimal working example look like?

Below is a complete script that sets up the pipeline, and generate an image from a prompt.

import torch

from pruna_pro import PrunaProModel


class Predictor:
    def setup(self):
        import logging

        logging.basicConfig(level=logging.INFO)
        self.pipe = PrunaProModel.from_pretrained(
            "PrunaAI/Qwen-Image-Edit-Plus",
            token="PRUNA_TOKEN",
            hf_token="HF_TOKEN",
            verbose=True,  # If supported by PrunaProModel
            log_level="info",  # If supported
        )

    def predict(
        self,
        prompt,
        image,
        go_fast=True,
        seed=None,
    ):
        generator = (
            torch.Generator("cuda").manual_seed(seed) if seed is not None else None
        )
        height, width = ASPECT_RATIOS[aspect_ratio]
        if go_fast:
            num_inference_steps = 8
        else:
            num_inference_steps = 16
        with torch.inference_mode(), torch.no_grad():
            image = self.pipe(
                prompt=prompt,
                image=image,
                true_cfg_scale=1.0,
                num_inference_steps=num_inference_steps,
                generator=generator,
            ).images[0]

        image.save("output.png")
        return "output.png"

if __name__ == "__main__":
    predictor = Predictor()
    predictor.setup()
    from diffusers.utils import load_image
    image = load_image("https://replicate.delivery/pbxt/NlPRwVX3rSb1lr6dcJw8F1QzBW8dcvFEuvJ3aygYi9iD6W4s/qwen-pose2.png")
    image_2 = load_image("https://replicate.delivery/pbxt/NlPRvwAlhPyevZ04BY6TEQmIjGYGxW1z9QHiLKabroVnmGe7/replicate-prediction-2rq8q6nrg5rmc0csex6818jzk8.jpeg")
    prompt = "The woman in image 2 adopts the pose from image 1"
    output = predictor.predict(
        prompt="'Bookstore window display. A sign displays “New Arrivals This Week”. Below, a shelf tag with the text “Best-Selling Novels Here”. To the side, a colorful poster advertises “Author Meet And Greet on Saturday” with a central portrait of the author. There are four books on the bookshelf, namely “The light between worlds” “When stars are scattered” “The slient patient” “The night circus”'",
        image=[image, image_2],
    )
    print(output)