Spaces:
Runtime error
Runtime error
File size: 3,806 Bytes
00e7506 8bf5a04 6cddac6 8bf5a04 00e7506 4cd25c8 8bf5a04 4cd25c8 f5929dc 00e7506 4cd25c8 00e7506 4cd25c8 6cddac6 8bf5a04 6cddac6 8bf5a04 6cddac6 8bf5a04 6cddac6 4cd25c8 6cddac6 4cd25c8 6cddac6 4cd25c8 6cddac6 4cd25c8 cf81290 4cd25c8 6cddac6 00e7506 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
import torch
import requests
import rembg
import random
import gradio as gr
import numpy
from PIL import Image
from diffusers import DiffusionPipeline, EulerAncestralDiscreteScheduler
# Load the pipeline
pipeline = DiffusionPipeline.from_pretrained(
"sudo-ai/zero123plus-v1.1", custom_pipeline="sudo-ai/zero123plus-pipeline",
torch_dtype=torch.float16
)
# Feel free to tune the scheduler!
# `timestep_spacing` parameter is not supported in older versions of `diffusers`
# so there may be performance degradations
# We recommend using `diffusers==0.20.2`
pipeline.scheduler = EulerAncestralDiscreteScheduler.from_config(
pipeline.scheduler.config, timestep_spacing='trailing'
)
pipeline.to('cuda:0')
def inference(input_img, num_inference_steps, guidance_scale, seed ):
# Download an example image.
cond = Image.open(input_img)
if seed==0:
seed = random.randint(1, 1000000)
# Run the pipeline!
#result = pipeline(cond, num_inference_steps=75).images[0]
result = pipeline(cond, num_inference_steps=num_inference_steps,
guidance_scale=guidance_scale,
generator=torch.Generator(pipeline.device).manual_seed(int(seed))).images[0]
# for general real and synthetic images of general objects
# usually it is enough to have around 28 inference steps
# for images with delicate details like faces (real or anime)
# you may need 75-100 steps for the details to construct
#result.show()
#result.save("output.png")
return result
def remove_background(result):
print(type(result))
# Check if the variable is a PIL Image
if isinstance(result, Image.Image):
print('here IF')
result = rembg.remove(result)
# Check if the variable is a str filepath
elif isinstance(result, str):
print('here ELIF')
result = Image.open(result)
result = rembg.remove(result)
elif isinstance(result, numpy.ndarray):
print('here ELIF 2')
# Convert the NumPy array to a PIL Image
result = Image.fromarray(result)
return result
# Create a Gradio interface for the Zero123++ model
with gr.Blocks() as demo:
# Display a title
gr.HTML("<h1><center> Interactive WebUI : Zero123++ </center></h1>")
gr.HTML("<h3><center> A Single Image to Consistent Multi-view Diffusion Base Model</center></h1>")
gr.HTML('''<center> <a href='https://arxiv.org/abs/2310.15110' target='_blank'>ArXiv</a> - <a href='https://github.com/SUDO-AI-3D/zero123plus/tree/main' target='_blank'>Code</a> </center>''')
with gr.Row():
# Input section: Allow users to upload an image
with gr.Column():
input_img = gr.Image(label='Input Image', type='filepath')
# Output section: Display the Zero123++ output image
with gr.Column():
output_img = gr.Image(label='Zero123++ Output')
# Submit button to initiate the inference
btn = gr.Button('Submit')
# Advanced options section with accordion for hiding/showing
with gr.Accordion("Advanced options:", open=False):
rm_in_bkg = gr.Checkbox(label='Remove Input Background')
rm_out_bkg = gr.Checkbox(label='Remove Output Background')
num_inference_steps = gr.Slider(label="Number of Inference Steps", minimum=15, maximum=100, step=1, value=75, interactive=True)
guidance_scale = gr.Slider(label="Classifier Free Guidance Scale", minimum=1.00, maximum=10.00, step=0.1, value=4.0, interactive=True)
seed = gr.Number(0, label='Seed')
btn.click(inference, [input_img, num_inference_steps, guidance_scale, seed ], output_img)
rm_in_bkg.input(remove_background, input_img, input_img)
rm_out_bkg.input(remove_background, output_img, output_img)
demo.launch(debug=True)
|