import gradio as gr
import torch
import numpy as np
import diffusers
import os
import spaces
from PIL import Image
hf_token = os.environ.get("HF_TOKEN")
from diffusers import StableDiffusionXLInpaintPipeline, DDIMScheduler, UNet2DConditionModel
ratios_map = {
0.5:{"width":704,"height":1408},
0.57:{"width":768,"height":1344},
0.68:{"width":832,"height":1216},
0.72:{"width":832,"height":1152},
0.78:{"width":896,"height":1152},
0.82:{"width":896,"height":1088},
0.88:{"width":960,"height":1088},
0.94:{"width":960,"height":1024},
1.00:{"width":1024,"height":1024},
1.13:{"width":1088,"height":960},
1.21:{"width":1088,"height":896},
1.29:{"width":1152,"height":896},
1.38:{"width":1152,"height":832},
1.46:{"width":1216,"height":832},
1.67:{"width":1280,"height":768},
1.75:{"width":1344,"height":768},
2.00:{"width":1408,"height":704}
}
ratios = np.array(list(ratios_map.keys()))
def get_size(init_image):
w,h=init_image.size
curr_ratio = w/h
ind = np.argmin(np.abs(curr_ratio-ratios))
ratio = ratios[ind]
chosen_ratio = ratios_map[ratio]
w,h = chosen_ratio['width'], chosen_ratio['height']
return w,h
device = "cuda" if torch.cuda.is_available() else "cpu"
unet = UNet2DConditionModel.from_pretrained(
"briaai/BRIA-2.3-Inpainting",
subfolder="unet",
torch_dtype=torch.float16,
)
scheduler = DDIMScheduler.from_pretrained("briaai/BRIA-2.3", subfolder="scheduler",
rescale_betas_zero_snr=True,prediction_type='v_prediction',timestep_spacing="trailing",clip_sample=False)
pipe = StableDiffusionXLInpaintPipeline.from_pretrained(
"briaai/BRIA-2.3",
unet=unet,
scheduler=scheduler,
torch_dtype=torch.float16,
force_zeros_for_empty_prompt=False
)
pipe = pipe.to(device)
pipe.force_zeros_for_empty_prompt = False
default_negative_prompt= "" #"Logo,Watermark,Text,Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate,Mutilated,Mutilated hands,Poorly drawn face,Deformed,Bad anatomy,Cloned face,Malformed limbs,Missing legs,Too many fingers"
def read_content(file_path: str) -> str:
"""read the content of target file
"""
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
return content
@spaces.GPU(enable_queue=True)
def predict(dict, prompt="", negative_prompt="", guidance_scale=5, steps=30, strength=1.0):
if negative_prompt == "":
negative_prompt = None
init_image = Image.fromarray(dict['background'][:, :, :3], 'RGB') #dict['background'].convert("RGB")#.resize((1024, 1024))
mask = Image.fromarray(dict['layers'][0][:,:,3], 'L') #dict['layers'].convert("RGB")#.resize((1024, 1024))
w,h = get_size(init_image)
init_image = init_image.resize((w, h))
mask = mask.resize((w, h))
# Resize to nearest ratio ?
mask = np.array(mask)
mask[mask>0]=255
mask = Image.fromarray(mask)
output = pipe(prompt = prompt,width=w,height=h, negative_prompt=negative_prompt, image=init_image, mask_image=mask, guidance_scale=guidance_scale, num_inference_steps=int(steps), strength=strength)
return output.images[0] #, gr.update(visible=True)
css = '''
.gradio-container{max-width: 1100px !important}
#image_upload{min-height:400px}
#image_upload [data-testid="image"], #image_upload [data-testid="image"] > div{min-height: 400px}
#mask_radio .gr-form{background:transparent; border: none}
#word_mask{margin-top: .75em !important}
#word_mask textarea:disabled{opacity: 0.3}
.footer {margin-bottom: 45px;margin-top: 35px;text-align: center;border-bottom: 1px solid #e5e5e5}
.footer>p {font-size: .8rem; display: inline-block; padding: 0 10px;transform: translateY(10px);background: white}
.dark .footer {border-color: #303030}
.dark .footer>p {background: #0b0f19}
.acknowledgments h4{margin: 1.25em 0 .25em 0;font-weight: bold;font-size: 115%}
#image_upload .touch-none{display: flex}
@keyframes spin {
from {
transform: rotate(0deg);
}
to {
transform: rotate(360deg);
}
}
#share-btn-container {padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; max-width: 13rem; margin-left: auto;}
div#share-btn-container > div {flex-direction: row;background: black;align-items: center}
#share-btn-container:hover {background-color: #060606}
#share-btn {all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.5rem !important; padding-bottom: 0.5rem !important;right:0;}
#share-btn * {all: unset}
#share-btn-container div:nth-child(-n+2){width: auto !important;min-height: 0px !important;}
#share-btn-container .wrap {display: none !important}
#share-btn-container.hidden {display: none!important}
#prompt input{width: calc(100% - 160px);border-top-right-radius: 0px;border-bottom-right-radius: 0px;}
#run_button{position:absolute;margin-top: 11px;right: 0;margin-right: 0.8em;border-bottom-left-radius: 0px;
border-top-left-radius: 0px;}
#prompt-container{margin-top:-18px;}
#prompt-container .form{border-top-left-radius: 0;border-top-right-radius: 0}
#image_upload{border-bottom-left-radius: 0px;border-bottom-right-radius: 0px}
'''
image_blocks = gr.Blocks(css=css, elem_id="total-container")
with image_blocks as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown("## BRIA 2.3")
gr.HTML('''
This is a demo for
BRIA 2.3 text-to-image .
BRIA 2.3 improve the generation of humans and illustrations compared to BRIA 2.2 while still trained on licensed data, and so provide full legal liability coverage for copyright and privacy infringement.
''')
with gr.Row():
with gr.Column():
image = gr.ImageEditor(sources=["upload"], layers=False, transforms=[], brush=gr.Brush(colors=["#000000"], color_mode="fixed")) #gr.Image(sources=['upload'], tool='sketch', elem_id="image_upload", type="pil", label="Upload", height=400)
with gr.Row(elem_id="prompt-container", equal_height=True):
with gr.Row():
prompt = gr.Textbox(placeholder="Your prompt (what you want in place of what is erased)", show_label=False, elem_id="prompt")
btn = gr.Button("Inpaint!", elem_id="run_button")
with gr.Accordion(label="Advanced Settings", open=False):
with gr.Row(equal_height=True):
guidance_scale = gr.Number(value=5, minimum=1.0, maximum=10.0, step=0.5, label="guidance_scale")
steps = gr.Number(value=30, minimum=20, maximum=50, step=1, label="steps")
strength = gr.Number(value=1, minimum=0.01, maximum=1.0, step=0.01, label="strength")
negative_prompt = gr.Textbox(label="negative_prompt", value=default_negative_prompt, placeholder=default_negative_prompt, info="what you don't want to see in the image")
with gr.Column():
image_out = gr.Image(label="Output", elem_id="output-img", height=400)
btn.click(fn=predict, inputs=[image, prompt, negative_prompt, guidance_scale, steps, strength], outputs=[image_out], api_name='run')
prompt.submit(fn=predict, inputs=[image, prompt, negative_prompt, guidance_scale, steps, strength], outputs=[image_out])
# gr.Examples(
# examples=[
# ["./imgs/example.png"],
# ],
# fn=predict,
# inputs=[image],
# cache_examples=False,
# )
gr.HTML(
"""
"""
)
image_blocks.queue(max_size=25,api_open=False).launch(show_api=False)