import logging import os import gradio as gr import numpy as np from PIL import Image from huggingface_hub import hf_hub_url, hf_hub_download from inference.face_detector import StatRetinaFaceDetector from inference.model_pipeline import VSNetModelPipeline from inference.onnx_model import ONNXModel logging.basicConfig( format='%(asctime)s %(levelname)-8s %(message)s', level=logging.INFO, datefmt='%Y-%m-%d %H:%M:%S') MODEL_IMG_SIZE = 512 usage_count = 82 # Based on hugging face logs def load_model(): REPO_ID = "Podtekatel/ArcaneVSK2" FILENAME_OLD = "arcane_exp_230_ep_136_512_res_V2_lighter.onnx" global model_old global pipeline_old # Old model model_path = hf_hub_download(REPO_ID, FILENAME_OLD, use_auth_token=os.getenv('HF_TOKEN')) model_old = ONNXModel(model_path) pipeline_old = VSNetModelPipeline(model_old, StatRetinaFaceDetector(MODEL_IMG_SIZE), background_resize=1024, no_detected_resize=1024) return model_old load_model() def inference(img): img = np.array(img) out_img = pipeline_old(img) out_img = Image.fromarray(out_img) global usage_count usage_count += 1 logging.info(f'Usage count is {usage_count}') return out_img title = "ARCNStyleTransferV2" description = "Gradio Demo for Arcane Season 1 style transfer. To use it, simply upload your image, or click one of the examples to load them. Press ❤️ if you like this space!" article = "This is one of my successful experiments on style transfer. I've built my own pipeline, generator model and private dataset to train this model
" \ "" \ "" \ "" \ "Model pipeline which used in project is improved CartoonGAN.
" \ "This model was trained on RTX 2080 Ti 3 days with batch size 7.
" \ "Model weights 80 MB in ONNX fp32 format, infers 100 ms on GPU and 600 ms on CPU at 512x512 resolution.
" \ "If you want to use this app or integrate this model into yours, please contact me at email 'neuromancer.ai.lover@gmail.com'." imgs_folder = 'demo' examples = [[os.path.join(imgs_folder, img_filename)] for img_filename in sorted(os.listdir(imgs_folder))] demo = gr.Interface( fn=inference, inputs=[gr.Image(type="pil")], outputs=gr.Image(type="pil"), title=title, description=description, article=article, examples=examples) demo.queue() demo.launch()