import gradio as gr
import torch
import numpy as np
import diffusers
import os
from PIL import Image
hf_token = os.environ.get("HF_TOKEN")
from diffusers import StableDiffusionXLInpaintPipeline, DDIMScheduler, UNet2DConditionModel
from diffusers import (
AutoencoderKL,
LCMScheduler,
)
from pipeline_controlnet_sd_xl import StableDiffusionXLControlNetPipeline
from controlnet import ControlNetModel, ControlNetConditioningEmbedding
import torch
import numpy as np
from PIL import Image
import requests
import PIL
from io import BytesIO
from torchvision import transforms
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()))
image_transforms = transforms.Compose(
[
transforms.ToTensor(),
]
)
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 get_masked_image(image, image_mask, width, height):
image_mask = image_mask # inpaint area is white
image_mask = image_mask.resize((width, height)) # object to remove is white (1)
image_mask_pil = image_mask
image = np.array(image.convert("RGB")).astype(np.float32) / 255.0
image_mask = np.array(image_mask_pil.convert("L")).astype(np.float32) / 255.0
assert image.shape[0:1] == image_mask.shape[0:1], "image and image_mask must have the same image size"
masked_image_to_present = image.copy()
masked_image_to_present[image_mask > 0.5] = (0.5,0.5,0.5) # set as masked pixel
image[image_mask > 0.5] = 0.5 # set as masked pixel - s.t. will be grey
image = Image.fromarray((image * 255.0).astype(np.uint8))
masked_image_to_present = Image.fromarray((masked_image_to_present * 255.0).astype(np.uint8))
return image, image_mask_pil, masked_image_to_present
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"
# Load, init model
controlnet = ControlNetModel().from_config('briaai/DEV-ControlNetInpaintingFast', torch_dtype=torch.float16)
controlnet.controlnet_cond_embedding = ControlNetConditioningEmbedding(
conditioning_embedding_channels=320,
conditioning_channels = 5
)
# controlnet = ControlNetModel().from_pretrained("briaai/DEV-ControlNetInpaintingFast", torch_dtype=torch.float16)
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = StableDiffusionXLControlNetPipeline.from_pretrained("briaai/BRIA-2.3", controlnet=controlnet.to(dtype=torch.float16), torch_dtype=torch.float16, vae=vae) #force_zeros_for_empty_prompt=False, # vae=vae)
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.load_lora_weights("briaai/BRIA-2.3-FAST-LORA")
pipe.fuse_lora()
pipe = pipe.to(device)
# pipe.enable_xformers_memory_efficient_attention()
generator = torch.Generator(device='cuda').manual_seed(123456)
vae = pipe.vae
pipe.enable_model_cpu_offload()
# 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
def predict(dict, prompt="", negative_prompt = default_negative_prompt, guidance_scale=1.2, steps=12, strength=1.0):
if negative_prompt == "":
negative_prompt = None
init_image = dict["image"].convert("RGB").resize((1024, 1024))
mask = dict["mask"].convert("L").resize((1024, 1024))
width, height = get_size(init_image)
init_image = init_image.resize((width, height))
mask = mask.resize((width, height))
# Resize to nearest ratio ?
# mask = np.array(mask)
# mask[mask>0]=255
# mask = Image.fromarray(mask)
masked_image, image_mask, masked_image_to_present = get_masked_image(init_image, mask, width, height)
masked_image_tensor = image_transforms(masked_image)
masked_image_tensor = (masked_image_tensor - 0.5) / 0.5
masked_image_tensor = masked_image_tensor.unsqueeze(0).to(device="cuda")
control_latents = vae.encode(
masked_image_tensor[:, :3, :, :].to(vae.dtype)
).latent_dist.sample()
control_latents = control_latents * vae.config.scaling_factor
image_mask = np.array(image_mask)[:,:]
mask_tensor = torch.tensor(image_mask, dtype=torch.float32)[None, ...]
# binarize the mask
mask_tensor = torch.where(mask_tensor > 128.0, 255.0, 0)
mask_tensor = mask_tensor / 255.0
mask_tensor = mask_tensor.to(device="cuda")
mask_resized = torch.nn.functional.interpolate(mask_tensor[None, ...], size=(control_latents.shape[2], control_latents.shape[3]), mode='nearest')
# mask_resized = mask_resized.to(torch.float16)
masked_image = torch.cat([control_latents, mask_resized], dim=1)
output = pipe(prompt = prompt,
width=width,
height=height,
negative_prompt=negative_prompt,
image = masked_image, # control image V
init_image = init_image,
mask_image=mask_tensor,
guidance_scale=guidance_scale,
num_inference_steps=int(steps),
# strength=strength,
generator=generator,
controlnet_conditioning_sale=1.0)
# gen_img = pipe(negative_prompt=default_negative_prompt, prompt=prompt,
# controlnet_conditioning_sale=1.0,
# num_inference_steps=12,
# height=height, width=width,
# image = masked_image, # control image
# init_image = init_image,
# mask_image = mask_tensor,
# guidance_scale = 1.2,
# generator=generator).images[0]
torch.cuda.empty_cache
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 2.2")
gr.HTML('''
This is a demo for
BRIA 2.2 text-to-image .
BRIA 2.2 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.Image(sources=['upload'], elem_id="image_upload", tool='sketch', 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=1.2, minimum=1.0, maximum=2, step=0.1, label="guidance_scale")
steps = gr.Number(value=12, minimum=8, maximum=30, 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.HTML(
"""
"""
)
image_blocks.queue(max_size=25,api_open=False).launch(show_api=False)