gradio/demo/animeganv2/run.ipynb
aliabid94 9b42ba8f10
Update guides esp plots (#8907)
* changes

* changes

* revert changes

* changes

* add changeset

* notebooks script

* changes

* changes

---------

Co-authored-by: Ali Abid <aliabid94@gmail.com>
Co-authored-by: gradio-pr-bot <gradio-pr-bot@users.noreply.github.com>
Co-authored-by: Ali Abdalla <ali.si3luwa@gmail.com>
2024-07-29 22:08:51 -07:00

2.9 KiB

Gradio Demo: animeganv2

Recreate the viral AnimeGAN image transformation demo.

    
In [ ]:
!pip install -q gradio torch torchvision Pillow gdown numpy scipy cmake onnxruntime-gpu opencv-python-headless
In [ ]:
# Downloading files from the demo repo
import os
!wget -q https://github.com/gradio-app/gradio/raw/main/demo/animeganv2/gongyoo.jpeg
!wget -q https://github.com/gradio-app/gradio/raw/main/demo/animeganv2/groot.jpeg
In [ ]:
import gradio as gr
import torch

model2 = torch.hub.load(
    "AK391/animegan2-pytorch:main",
    "generator",
    pretrained=True,
    progress=False
)
model1 = torch.hub.load("AK391/animegan2-pytorch:main", "generator", pretrained="face_paint_512_v1")
face2paint = torch.hub.load(
    'AK391/animegan2-pytorch:main', 'face2paint',
    size=512,side_by_side=False
)

def inference(img, ver):
    if ver == 'version 2 (🔺 robustness,🔻 stylization)':
        out = face2paint(model2, img)
    else:
        out = face2paint(model1, img)
    return out

title = "AnimeGANv2"
description = "Gradio Demo for AnimeGanv2 Face Portrait. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below. Please use a cropped portrait picture for best results similar to the examples below."
article = "<p style='text-align: center'><a href='https://github.com/bryandlee/animegan2-pytorch' target='_blank'>Github Repo Pytorch</a></p> <center><img src='https://visitor-badge.glitch.me/badge?page_id=akhaliq_animegan' alt='visitor badge'></center></p>"
examples=[['groot.jpeg','version 2 (🔺 robustness,🔻 stylization)'],['gongyoo.jpeg','version 1 (🔺 stylization, 🔻 robustness)']]

demo = gr.Interface(
    fn=inference,
    inputs=[gr.Image(type="pil"),gr.Radio(['version 1 (🔺 stylization, 🔻 robustness)','version 2 (🔺 robustness,🔻 stylization)'], type="value", value='version 2 (🔺 robustness,🔻 stylization)', label='version')],
    outputs=gr.Image(type="pil"),
    title=title,
    description=description,
    article=article,
    examples=examples)

demo.launch()