import os from posixpath import basename import torch import gradio as gr import os import sys import numpy as np from e4e.models.psp import pSp from util import * from huggingface_hub import hf_hub_download import os import sys import tempfile import shutil from argparse import Namespace from pathlib import Path import shutil import dlib import numpy as np import torchvision.transforms as transforms from torchvision import utils from PIL import Image from model.sg2_model import Generator from generate_videos import generate_frames, video_from_interpolations, vid_to_gif model_dir = "models" os.makedirs(model_dir, exist_ok=True) model_repos = {"e4e": ("akhaliq/JoJoGAN_e4e_ffhq_encode", "e4e_ffhq_encode.pt"), "dlib": ("akhaliq/jojogan_dlib", "shape_predictor_68_face_landmarks.dat"), "base": ("akhaliq/jojogan-stylegan2-ffhq-config-f", "stylegan2-ffhq-config-f.pt"), "anime": ("rinong/stylegan-nada-models", "anime.pt"), "joker": ("rinong/stylegan-nada-models", "joker.pt"), # "simpson": ("rinong/stylegan-nada-models", "simpson.pt"), # "ssj": ("rinong/stylegan-nada-models", "ssj.pt"), # "white_walker": ("rinong/stylegan-nada-models", "white_walker.pt"), # "zuckerberg": ("rinong/stylegan-nada-models", "zuckerberg.pt"), # "cubism": ("rinong/stylegan-nada-models", "cubism.pt"), # "disney_princess": ("rinong/stylegan-nada-models", "disney_princess.pt"), # "edvard_munch": ("rinong/stylegan-nada-models", "edvard_munch.pt"), # "van_gogh": ("rinong/stylegan-nada-models", "van_gogh.pt"), # "oil": ("rinong/stylegan-nada-models", "oil.pt"), # "rick_morty": ("rinong/stylegan-nada-models", "rick_morty.pt"), # "botero": ("rinong/stylegan-nada-models", "botero.pt"), # "crochet": ("rinong/stylegan-nada-models", "crochet.pt"), # "modigliani": ("rinong/stylegan-nada-models", "modigliani.pt"), # "shrek": ("rinong/stylegan-nada-models", "shrek.pt"), # "sketch": ("rinong/stylegan-nada-models", "sketch.pt"), # "thanos": ("rinong/stylegan-nada-models", "thanos.pt"), } def get_models(): os.makedirs(model_dir, exist_ok=True) model_paths = {} for model_name, repo_details in model_repos.items(): download_path = hf_hub_download(repo_id=repo_details[0], filename=repo_details[1]) model_paths[model_name] = download_path return model_paths model_paths = get_models() class ImageEditor(object): def __init__(self): self.device = "cuda" if torch.cuda.is_available() else "cpu" latent_size = 512 n_mlp = 8 channel_mult = 2 model_size = 1024 self.generators = {} self.model_list = [name for name in model_paths.keys() if name not in ["e4e", "dlib"]] for model in self.model_list: g_ema = Generator( model_size, latent_size, n_mlp, channel_multiplier=channel_mult ).to(self.device) checkpoint = torch.load(model_paths[model], map_location=self.device) g_ema.load_state_dict(checkpoint['g_ema']) self.generators[model] = g_ema self.experiment_args = {"model_path": model_paths["e4e"]} self.experiment_args["transform"] = transforms.Compose( [ transforms.Resize((256, 256)), transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]), ] ) self.resize_dims = (256, 256) model_path = self.experiment_args["model_path"] ckpt = torch.load(model_path, map_location="cpu") opts = ckpt["opts"] opts["checkpoint_path"] = model_path opts = Namespace(**opts) self.e4e_net = pSp(opts, self.device) self.e4e_net.eval() self.shape_predictor = dlib.shape_predictor( model_paths["dlib"] ) print("setup complete") def get_style_list(self): # style_list = ['all', 'list - enter below'] style_list = [] for key in self.generators: style_list.append(key) return style_list def invert_image(self, input_image): input_image = self.run_alignment(str(input_image)) input_image = input_image.resize(self.resize_dims) img_transforms = self.experiment_args["transform"] transformed_image = img_transforms(input_image) with torch.no_grad(): images, latents = self.run_on_batch(transformed_image.unsqueeze(0)) result_image, latent = images[0], latents[0] inverted_latent = latent.unsqueeze(0).unsqueeze(1) return inverted_latent def get_generators_for_styles(self, output_styles, loop_styles=False): # if style_string: # styles = style_string.split(",") # for style in styles: # if style not in self.model_list: # raise ValueError(f"Encountered style '{style}' in the input style list which is not an available option.") # else: # styles = style_checkbox_list if "base" in output_styles: # always start with base if chosen output_styles.insert(0, output_styles.pop(output_styles.index("base"))) if loop_styles: output_styles.append(output_styles[0]) return [self.generators[style] for style in output_styles] def edit_image(self, input, output_styles): return self.predict(input, output_styles) def edit_video(self, input, output_styles, with_editing, video_format, loop_styles): return self.predict(input, output_styles, True, with_editing, video_format, loop_styles) def predict( self, input, # Input image path output_styles, # Style checkbox options. generate_video = False, # Generate a video instead of an output image with_editing = False, # Apply latent space editing to the generated video video_format = "mp4", # Choose gif to display in browser, mp4 for higher-quality downloadable video loop_styles = False, # Loop back to the initial style ): # @title Align image out_dir = Path(tempfile.mkdtemp()) out_path = out_dir / "out.jpg" inverted_latent = self.invert_image(input) generators = self.get_generators_for_styles(output_styles, loop_styles) if not generate_video: with torch.no_grad(): img_list = [] for g_ema in generators: img, _ = g_ema(inverted_latent, input_is_latent=True, truncation=1, randomize_noise=False) img_list.append(img) out_img = torch.cat(img_list, axis=0) utils.save_image(out_img, out_path, nrow=int(np.sqrt(out_img.size(0))), normalize=True, scale_each=True, range=(-1, 1)) return str(out_path) return self.generate_vid(generators, inverted_latent, out_dir, video_format, with_editing) def generate_vid(self, generators, latent, out_dir, video_format, with_editing): np_latent = latent.squeeze(0).cpu().detach().numpy() args = { 'fps': 24, 'target_latents': None, 'edit_directions': None, 'unedited_frames': 0 if with_editing else 40 * (len(generators) - 1) } args = Namespace(**args) with tempfile.TemporaryDirectory() as dirpath: generate_frames(args, np_latent, generators, dirpath) video_from_interpolations(args.fps, dirpath) gen_path = Path(dirpath) / "out.mp4" out_path = out_dir / f"out.{video_format}" if video_format == 'gif': vid_to_gif(gen_path, out_dir, scale=256, fps=args.fps) else: shutil.copy2(gen_path, out_path) return str(out_path) def run_alignment(self, image_path): aligned_image = align_face(filepath=image_path, predictor=self.shape_predictor) print("Aligned image has shape: {}".format(aligned_image.size)) return aligned_image def run_on_batch(self, inputs): images, latents = self.e4e_net( inputs.to(self.device).float(), randomize_noise=False, return_latents=True ) return images, latents editor = ImageEditor() def change_component_visibility(component_types, invert_choices): def visibility_impl(visible): return [component_types[idx].update(visible=visible ^ invert_choices[idx]) for idx in range(len(component_types))] return visibility_impl # def group_visibility(visible): # print("visible: ", visible) # return gr.Group.update(visibile=visible) blocks = gr.Blocks() with blocks: gr.Markdown("

StyleGAN-NADA

") gr.Markdown( "Demo for StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators (SIGGRAPH 2022)." ) gr.Markdown( "For more information about the paper and code for training your own models (with examples OR text), see below." ) with gr.Row(): with gr.Column(): input_img = gr.inputs.Image(type="filepath", label="Input image") style_choice = gr.inputs.CheckboxGroup(choices=editor.get_style_list(), type="value", label="Choose your styles!") video_choice = gr.inputs.Checkbox(default=False, label="Generate Video?", optional=False) loop_styles = gr.inputs.Checkbox(default=True, label="Loop video back to the initial style?", visible=False) edit_choice = gr.inputs.Checkbox(default=False, label="With Editing?", visible=False) vid_format_choice = gr.inputs.Radio(choices=["gif", "mp4"], type="value", default='mp4', label="Video Format", visible=False) # img_button = gr.Button("Edit Image") # vid_button = gr.Button("Generate Video") img_button = gr.Button("Edit Image") vid_button = gr.Button("Generate Video", visible=False) with gr.Column(): img_output = gr.outputs.Image(type="file") vid_output = gr.outputs.Video(visible=False) visibility_fn = change_component_visibility(component_types=[gr.Checkbox, gr.Radio, gr.Video, gr.Button, gr.Image, gr.Button, gr.Checkbox], invert_choices=[False, False, False, False, True, True, False]) video_choice.change(fn=visibility_fn, inputs=video_choice, outputs=[edit_choice, vid_format_choice, vid_output, vid_button, img_output, img_button]) # video_choice.change(fn=group_visibility, inputs=video_choice, outputs=video_options_group) img_button.click(fn=editor.edit_image, inputs=[input_img, style_choice], outputs=img_output) vid_button.click(fn=editor.edit_video, inputs=[input_img, style_choice, edit_choice, vid_format_choice, loop_styles], outputs=vid_output) # with gr.Row(): # input_img = gr.inputs.Image(type="filepath", label="Input image") # style_choice = gr.inputs.CheckboxGroup(choices=editor.get_style_list(), type="value", label="Choose your styles!") # with gr.Tabs(): # with gr.TabItem("Edit Images"): # with gr.Column(): # img_button = gr.Button("Edit Image") # with gr.Column(): # img_output = gr.outputs.Image(type="file", label="Output Image") # with gr.TabItem("Create Video"): # with gr.Column(): # with gr.Row(): # vid_button = gr.Button("Generate Video") # loop_styles = gr.inputs.Checkbox(default=True, label="Loop video back to the initial style?") # edit_choice = gr.inputs.Checkbox(default=False, label="With latent space editing?") # vid_format_choice = gr.inputs.Radio(choices=["gif", "mp4"], type="value", default='mp4', label="Video Format") # with gr.Column(): # vid_output = gr.outputs.Video(label="Output Video") # img_button.click(fn=editor.edit_image, inputs=[input_img, style_choice], outputs=img_output) # vid_button.click(fn=editor.edit_video, inputs=[input_img, style_choice, edit_choice, vid_format_choice, loop_styles], outputs=vid_output) article = "

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators | Project Page | Code

visitor badge
" gr.Markdown(article) blocks.launch(enable_queue=True)