File size: 5,051 Bytes
1239b39 |
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 |
from share import *
import config
import cv2
import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
from annotator.midas import MidasDetector
from cldm.model import create_model, load_state_dict
from cldm.ddim_hacked import DDIMSampler
apply_midas = MidasDetector()
model = create_model('./models/cldm_v15.yaml').cpu()
model.load_state_dict(load_state_dict('./models/control_sd15_normal.pth', location='cuda'))
model = model.cuda()
ddim_sampler = DDIMSampler(model)
def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, detect_resolution, ddim_steps, guess_mode, strength, scale, seed, eta, bg_threshold):
with torch.no_grad():
input_image = HWC3(input_image)
_, detected_map = apply_midas(resize_image(input_image, detect_resolution), bg_th=bg_threshold)
detected_map = HWC3(detected_map)
img = resize_image(input_image, image_resolution)
H, W, C = img.shape
detected_map = cv2.resize(detected_map, (W, H), interpolation=cv2.INTER_LINEAR)
control = torch.from_numpy(detected_map[:, :, ::-1].copy()).float().cuda() / 255.0
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 65535)
seed_everything(seed)
if config.save_memory:
model.low_vram_shift(is_diffusing=False)
cond = {"c_concat": [control], "c_crossattn": [model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
un_cond = {"c_concat": None if guess_mode else [control], "c_crossattn": [model.get_learned_conditioning([n_prompt] * num_samples)]}
shape = (4, H // 8, W // 8)
if config.save_memory:
model.low_vram_shift(is_diffusing=True)
model.control_scales = [strength * (0.825 ** float(12 - i)) for i in range(13)] if guess_mode else ([strength] * 13) # Magic number. IDK why. Perhaps because 0.825**12<0.01 but 0.826**12>0.01
samples, intermediates = ddim_sampler.sample(ddim_steps, num_samples,
shape, cond, verbose=False, eta=eta,
unconditional_guidance_scale=scale,
unconditional_conditioning=un_cond)
if config.save_memory:
model.low_vram_shift(is_diffusing=False)
x_samples = model.decode_first_stage(samples)
x_samples = (einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
results = [x_samples[i] for i in range(num_samples)]
return [detected_map] + results
block = gr.Blocks().queue()
with block:
with gr.Row():
gr.Markdown("## Control Stable Diffusion with Normal Maps")
with gr.Row():
with gr.Column():
input_image = gr.Image(source='upload', type="numpy")
prompt = gr.Textbox(label="Prompt")
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
detect_resolution = gr.Slider(label="Normal Resolution", minimum=128, maximum=1024, value=384, step=1)
bg_threshold = gr.Slider(label="Normal background threshold", minimum=0.0, maximum=1.0, value=0.4, step=0.01)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",
value='longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality')
with gr.Column():
result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery").style(grid=2, height='auto')
ips = [input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, detect_resolution, ddim_steps, guess_mode, strength, scale, seed, eta, bg_threshold]
run_button.click(fn=process, inputs=ips, outputs=[result_gallery])
block.launch(server_name='0.0.0.0')
|