Spaces:
Running
on
Zero
Running
on
Zero
File size: 6,915 Bytes
a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 abf3d6e a6d7aa6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 |
import spaces
import gradio as gr
from tryon_inference import run_inference
import os
import numpy as np
from PIL import Image
import tempfile
import torch
from diffusers import FluxTransformer2DModel, FluxFillPipeline
import shutil
def find_cuda():
# Check if CUDA_HOME or CUDA_PATH environment variables are set
cuda_home = os.environ.get('CUDA_HOME') or os.environ.get('CUDA_PATH')
if cuda_home and os.path.exists(cuda_home):
return cuda_home
# Search for the nvcc executable in the system's PATH
nvcc_path = shutil.which('nvcc')
if nvcc_path:
# Remove the 'bin/nvcc' part to get the CUDA installation path
cuda_path = os.path.dirname(os.path.dirname(nvcc_path))
return cuda_path
return None
cuda_path = find_cuda()
if cuda_path:
print(f"CUDA installation found at: {cuda_path}")
else:
print("CUDA installation not found")
device = torch.device('cuda')
print('Loading diffusion model ...')
transformer = FluxTransformer2DModel.from_pretrained(
"xiaozaa/catvton-flux-alpha",
torch_dtype=torch.bfloat16
)
pipe = FluxFillPipeline.from_pretrained(
"black-forest-labs/FLUX.1-dev",
transformer=transformer,
torch_dtype=torch.bfloat16
).to(device)
print('Loading Finished!')
@spaces.GPU
def gradio_inference(
image_data,
garment,
num_steps=50,
guidance_scale=30.0,
seed=-1,
width=768,
height=1024
):
"""Wrapper function for Gradio interface"""
# Use temporary directory
with tempfile.TemporaryDirectory() as tmp_dir:
# Save inputs to temp directory
temp_image = os.path.join(tmp_dir, "image.png")
temp_mask = os.path.join(tmp_dir, "mask.png")
temp_garment = os.path.join(tmp_dir, "garment.png")
# Extract image and mask from ImageEditor data
image = image_data["background"]
mask = image_data["layers"][0] # First layer contains the mask
# Convert to numpy array and process mask
mask_array = np.array(mask)
is_black = np.all(mask_array < 10, axis=2)
mask = Image.fromarray(((~is_black) * 255).astype(np.uint8))
# Save files to temp directory
image.save(temp_image)
mask.save(temp_mask)
garment.save(temp_garment)
try:
# Run inference
_, tryon_result = run_inference(
pipe=pipe,
image_path=temp_image,
mask_path=temp_mask,
garment_path=temp_garment,
num_steps=num_steps,
guidance_scale=guidance_scale,
seed=seed,
size=(width, height)
)
return tryon_result
except Exception as e:
raise gr.Error(f"Error during inference: {str(e)}")
with gr.Blocks() as demo:
gr.Markdown("""
# CATVTON FLUX Virtual Try-On Demo
Upload a model image, draw a mask, and a garment image to generate virtual try-on results.
[](https://huggingface.co/xiaozaa/catvton-flux-alpha)
[](https://github.com/nftblackmagic/catvton-flux)
""")
gr.Video("example/github.mp4", label="Demo Video: How to use the tool")
with gr.Column():
with gr.Row():
with gr.Column():
image_input = gr.ImageMask(
label="Model Image (Click 'Edit' and draw mask over the clothing area)",
type="pil",
height=600,
width=300
)
gr.Examples(
examples=[
["./example/person/00008_00.jpg"],
["./example/person/00055_00.jpg"],
["./example/person/00057_00.jpg"],
["./example/person/00067_00.jpg"],
["./example/person/00069_00.jpg"],
],
inputs=[image_input],
label="Person Images",
)
with gr.Column():
garment_input = gr.Image(label="Garment Image", type="pil", height=600, width=300)
gr.Examples(
examples=[
["./example/garment/04564_00.jpg"],
["./example/garment/00055_00.jpg"],
["./example/garment/00396_00.jpg"],
["./example/garment/00067_00.jpg"],
["./example/garment/00069_00.jpg"],
],
inputs=[garment_input],
label="Garment Images",
)
with gr.Column():
tryon_output = gr.Image(label="Try-On Result", height=600, width=300)
with gr.Row():
num_steps = gr.Slider(
minimum=1,
maximum=100,
value=30,
step=1,
label="Number of Steps"
)
guidance_scale = gr.Slider(
minimum=1.0,
maximum=50.0,
value=30.0,
step=0.5,
label="Guidance Scale"
)
seed = gr.Slider(
minimum=-1,
maximum=2147483647,
step=1,
value=-1,
label="Seed (-1 for random)"
)
width = gr.Slider(
minimum=256,
maximum=1024,
step=64,
value=768,
label="Width"
)
height = gr.Slider(
minimum=256,
maximum=1024,
step=64,
value=1024,
label="Height"
)
submit_btn = gr.Button("Generate Try-On", variant="primary")
with gr.Row():
gr.Markdown("""
### Notes:
- The model is trained on VITON-HD dataset. It focuses on the woman upper body try-on generation.
- The mask should indicate the region where the garment will be placed.
- The garment image should be on a clean background.
- The model is not perfect. It may generate some artifacts.
- The model is slow. Please be patient.
- The model is just for research purpose.
""")
submit_btn.click(
fn=gradio_inference,
inputs=[
image_input,
garment_input,
num_steps,
guidance_scale,
seed,
width,
height
],
outputs=[tryon_output],
api_name="try-on"
)
demo.launch() |