app.py

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('cuda:0')
pipe.enable_xformers_memory_efficient_attention()

generator = torch.Generator(device='cuda:0').manual_seed(123456)

vae = pipe.vae


# 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]

    
    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('''
          <p style="margin-bottom: 10px; font-size: 94%">
            This is a demo for 
            <a href="https://huggingface.co/briaai/BRIA-2.2" target="_blank">BRIA 2.2 text-to-image </a>. 
            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.
          </p>
        ''')
    with gr.Row():
                with gr.Column():
                    image = 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.HTML(
        """
            <div class="footer">
                <p>Model by <a href="https://huggingface.co/diffusers" style="text-decoration: underline;" target="_blank">Diffusers</a> - Gradio Demo by 🤗 Hugging Face
                </p>
            </div>
        """
    )

image_blocks.queue(max_size=25,api_open=False).launch(show_api=False)