Spaces:
Sleeping
Sleeping
File size: 5,531 Bytes
48d3a70 f611314 54507dc f611314 54507dc fab2b8a f611314 2d7003c f611314 54507dc f611314 |
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 |
import spaces
from diffusers import ControlNetModel
from diffusers import StableDiffusionXLControlNetPipeline
from diffusers import EulerAncestralDiscreteScheduler
from PIL import Image
import torch
import numpy as np
import cv2
import gradio as gr
from torchvision import transforms
from controlnet_aux import OpenposeDetector
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()))
openpose = OpenposeDetector.from_pretrained('lllyasviel/ControlNet')
controlnet = ControlNetModel.from_pretrained(
"briaai/BRIA-2.3-ControlNet-Pose",
torch_dtype=torch.float16
).to('cuda')
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
"briaai/BRIA-2.3",
controlnet=controlnet,
torch_dtype=torch.float16,
low_cpu_mem_usage=True,
offload_state_dict=True,
).to('cuda').to(torch.float16)
pipe.scheduler = EulerAncestralDiscreteScheduler(
beta_start=0.00085,
beta_end=0.012,
beta_schedule="scaled_linear",
num_train_timesteps=1000,
steps_offset=1
)
# pipe.enable_freeu(b1=1.1, b2=1.1, s1=0.5, s2=0.7)
# pipe.enable_xformers_memory_efficient_attention()
pipe.force_zeros_for_empty_prompt = False
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
def resize_image(image):
image = image.convert('RGB')
w,h = get_size(image)
resized_image = image.resize((w, h))
return resized_image
def resize_image_old(image):
image = image.convert('RGB')
current_size = image.size
if current_size[0] > current_size[1]:
center_cropped_image = transforms.functional.center_crop(image, (current_size[1], current_size[1]))
else:
center_cropped_image = transforms.functional.center_crop(image, (current_size[0], current_size[0]))
resized_image = transforms.functional.resize(center_cropped_image, (1024, 1024))
return resized_image
@spaces.GPU
def generate_(prompt, negative_prompt, pose_image, input_image, num_steps, controlnet_conditioning_scale, seed):
generator = torch.Generator("cuda").manual_seed(seed)
images = pipe(
prompt, negative_prompt=negative_prompt, image=pose_image, num_inference_steps=num_steps, controlnet_conditioning_scale=float(controlnet_conditioning_scale),
generator=generator, height=input_image.size[1], width=input_image.size[0],
).images
return images
@spaces.GPU
def process(input_image, prompt, negative_prompt, num_steps, controlnet_conditioning_scale, seed):
# resize input_image to 1024x1024
input_image = resize_image(input_image)
pose_image = openpose(input_image, include_body=True, include_hand=True, include_face=True)
images = generate_(prompt, negative_prompt, pose_image, input_image, num_steps, controlnet_conditioning_scale, seed)
return [pose_image,images[0]]
block = gr.Blocks().queue()
with block:
gr.Markdown("## BRIA 2.3 ControlNet Pose")
gr.HTML('''
<p style="margin-bottom: 10px; font-size: 94%">
This is a demo for ControlNet Pose that using
<a href="https://huggingface.co/briaai/BRIA-2.3" target="_blank">BRIA 2.3 text-to-image model</a> as backbone.
Trained on licensed data, BRIA 2.3 provide full legal liability coverage for copyright and privacy infringement.
</p>
''')
with gr.Row():
with gr.Column():
input_image = gr.Image(sources=None, type="pil") # None for upload, ctrl+v and webcam
prompt = gr.Textbox(label="Prompt")
negative_prompt = gr.Textbox(label="Negative prompt", value="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")
num_steps = gr.Slider(label="Number of steps", minimum=25, maximum=100, value=50, step=1)
controlnet_conditioning_scale = gr.Slider(label="ControlNet conditioning scale", minimum=0.1, maximum=2.0, value=1.0, step=0.05)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True,)
run_button = gr.Button(value="Run")
with gr.Column():
with gr.Row():
pose_image_output = gr.Image(label="Pose Image", type="pil", interactive=False)
generated_image_output = gr.Image(label="Generated Image", type="pil", interactive=False)
ips = [input_image, prompt, negative_prompt, num_steps, controlnet_conditioning_scale, seed]
run_button.click(fn=process, inputs=ips, outputs=[pose_image_output, generated_image_output])
block.launch(debug = True) |