app.py

import torch
import spaces
import gradio as gr
from diffusers import FluxFillPipeline

pipe = FluxFillPipeline.from_pretrained("black-forest-labs/FLUX.1-Fill-dev", torch_dtype=torch.bfloat16).to("cuda")

# reference https://huggingface.co/spaces/black-forest-labs/FLUX.1-Fill-dev/blob/main/app.py 
def calculate_optimal_dimensions(image):
    # Extract the original dimensions
    original_width, original_height = image.size
    
    # Set constants
    MIN_ASPECT_RATIO = 9 / 16
    MAX_ASPECT_RATIO = 16 / 9
    FIXED_DIMENSION = 1024

    # Calculate the aspect ratio of the original image
    original_aspect_ratio = original_width / original_height

    # Determine which dimension to fix
    if original_aspect_ratio > 1:  # Wider than tall
        width = FIXED_DIMENSION
        height = round(FIXED_DIMENSION / original_aspect_ratio)
    else:  # Taller than wide
        height = FIXED_DIMENSION
        width = round(FIXED_DIMENSION * original_aspect_ratio)

    # Ensure dimensions are multiples of 8
    width = (width // 8) * 8
    height = (height // 8) * 8

    # Enforce aspect ratio limits
    calculated_aspect_ratio = width / height
    if calculated_aspect_ratio > MAX_ASPECT_RATIO:
        width = (height * MAX_ASPECT_RATIO // 8) * 8
    elif calculated_aspect_ratio < MIN_ASPECT_RATIO:
        height = (width / MIN_ASPECT_RATIO // 8) * 8

    # Ensure width and height remain above the minimum dimensions
    width = max(width, 576) if width == FIXED_DIMENSION else width
    height = max(height, 576) if height == FIXED_DIMENSION else height

    return width, height


@spaces.GPU(duration=120)
def inpaint(
    image,
    mask,
    prompt="",
    num_inference_steps=28,
    guidance_scale=50,
):
    image = image.convert("RGB")
    mask = mask.convert("L")
    width, height = calculate_optimal_dimensions(image)

    result = pipe(
        prompt=prompt,
        height= height,
        width= width,
        image= image,
        mask_image=mask,
        num_inference_steps=num_inference_steps,
        guidance_scale=guidance_scale,
    ).images[0]

    result = result.convert("RGBA")

    return result


demo = gr.Interface(
    fn=inpaint,
    inputs=[
        gr.Image(label="image", type="pil"),
        gr.Image(label="mask", type="pil"),
        gr.Text(label="prompt"),
        gr.Number(value=40, label="num_inference_steps"),
        gr.Number(value=28, label="guidance_scale"),
    ],
    outputs=["image"],
    api_name="inpaint",
    examples=[["./assets/rocket.png", "./assets/Inpainting mask.png"]],
    cache_examples=False,
    description="it is recommended that you use https://github.com/la-voliere/react-mask-editor when creating an image mask in JS and then inverse it before sending it to this space",
)

demo.launch()