import logging import random import warnings import os import gradio as gr import numpy as np import spaces import torch from diffusers import FluxControlNetModel from diffusers.pipelines import FluxControlNetPipeline from gradio_imageslider import ImageSlider from PIL import Image from huggingface_hub import snapshot_download css = """ #col-container { margin: 0 auto; max-width: 512px; } """ if torch.cuda.is_available(): power_device = "GPU" device = "cuda" else: power_device = "CPU" device = "cpu" huggingface_token = os.getenv("HUGGINFACE_TOKEN") model_path = snapshot_download( repo_id="black-forest-labs/FLUX.1-dev", repo_type="model", ignore_patterns=["*.md", "*..gitattributes"], local_dir="FLUX.1-dev", token=huggingface_token, # type a new token-id. ) # Load pipeline controlnet = FluxControlNetModel.from_pretrained( "jasperai/Flux.1-dev-Controlnet-Upscaler", torch_dtype=torch.bfloat16 ).to(device) pipe = FluxControlNetPipeline.from_pretrained( model_path, controlnet=controlnet, torch_dtype=torch.bfloat16 ) pipe.to(device) MAX_SEED = 1000000 MAX_PIXEL_BUDGET = 1024 * 1024 def process_input(input_image, upscale_factor, **kwargs): w, h = input_image.size w_original, h_original = w, h aspect_ratio = w / h was_resized = False if w * h * upscale_factor**2 > MAX_PIXEL_BUDGET: warnings.warn( f"Requested output image is too large ({w * upscale_factor}x{h * upscale_factor}). Resizing to ({int(aspect_ratio * MAX_PIXEL_BUDGET ** 0.5 // upscale_factor), int(MAX_PIXEL_BUDGET ** 0.5 // aspect_ratio // upscale_factor)}) pixels." ) gr.Info( f"Requested output image is too large ({w * upscale_factor}x{h * upscale_factor}). Resizing input to ({int(aspect_ratio * MAX_PIXEL_BUDGET ** 0.5 // upscale_factor), int(MAX_PIXEL_BUDGET ** 0.5 // aspect_ratio // upscale_factor)}) pixels budget." ) input_image = input_image.resize( ( int(aspect_ratio * MAX_PIXEL_BUDGET**0.5 // upscale_factor), int(MAX_PIXEL_BUDGET**0.5 // aspect_ratio // upscale_factor), ) ) was_resized = True # resize to multiple of 8 w, h = input_image.size w = w - w % 8 h = h - h % 8 return input_image.resize((w, h)), w_original, h_original, was_resized @spaces.GPU#(duration=42) def infer( seed, randomize_seed, input_image, num_inference_steps, upscale_factor, controlnet_conditioning_scale, progress=gr.Progress(track_tqdm=True), ): if randomize_seed: seed = random.randint(0, MAX_SEED) true_input_image = input_image input_image, w_original, h_original, was_resized = process_input( input_image, upscale_factor ) # rescale with upscale factor w, h = input_image.size control_image = input_image.resize((w * upscale_factor, h * upscale_factor)) generator = torch.Generator().manual_seed(seed) gr.Info("Upscaling image...") image = pipe( prompt="", control_image=control_image, controlnet_conditioning_scale=controlnet_conditioning_scale, num_inference_steps=num_inference_steps, guidance_scale=3.5, height=control_image.size[1], width=control_image.size[0], generator=generator, ).images[0] if was_resized: gr.Info( f"Resizing output image to targeted {w_original * upscale_factor}x{h_original * upscale_factor} size." ) # resize to target desired size image = image.resize((w_original * upscale_factor, h_original * upscale_factor)) image.save("output.jpg") # convert to numpy return [true_input_image, image, seed] with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css) as demo: # with gr.Column(elem_id="col-container"): gr.HTML("