文件superresolution.py功能是实现图像超分辨率处理的 Streamlit 应用。该应用允许用户上传低分辨率图像,输入提示文本以描述希望增强的内容,并通过 Stable Diffusion 模型生成高分辨率的图像。用户可以调整生成过程中的参数,如随机种子、样本数量、尺度、DDIM 步数和噪声水平等。程序通过将模型加载、图像处理和最终结果展示整合在一起,提供了一个简洁的界面来实现图像质量的提升。
1.1 加载模型
函数 initialize_model 的功能是加载和初始化给定配置文件中的模型,使用指定的检查点加载权重,并将模型移动到合适的设备(CPU 或 GPU),最后返回一个 DDIM 采样器实例。
@st.cache(allow_output_mutation=True)
def initialize_model(config, ckpt):
config = OmegaConf.load(config)
model = instantiate_from_config(config.model)
model.load_state_dict(torch.load(ckpt)["state_dict"], strict=False)
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
model = model.to(device)
sampler = DDIMSampler(model)
return sampler
1.2 格式转换
函数 make_batch_sd 的功能是将输入图像和提示文本转换为适合模型输入的批量格式,并将其移动到指定设备,同时支持生成多个样本。
def make_batch_sd(
image,
txt,
device,
num_samples=1,
):
image = np.array(image.convert("RGB"))
image = torch.from_numpy(image).to(dtype=torch.float32) / 127.5 - 1.0
batch = {
"lr": rearrange(image, 'h w c -> 1 c h w'),
"txt": num_samples * [txt],
}
batch["lr"] = repeat(batch["lr"].to(device=device), "1 ... -> n ...", n=num_samples)
return batch
1.3 生成增强后的图像
函数 make_noise_augmentation 的功能是根据输入的低分辨率图像和噪声水平,利用模型的低分辨率模型生成增强后的图像,并返回增强图像和噪声水平。
def make_noise_augmentation(model, batch, noise_level=None):
x_low = batch[model.low_scale_key]
x_low = x_low.to(memory_format=torch.contiguous_format).float()
x_aug, noise_level = model.low_scale_model(x_low, noise_level)
return x_aug, noise_level
1.4 超分辨率生成
函数 paint 的功能是执行超分辨率生成过程,使用采样器和输入图像、提示、种子、尺度、尺寸等参数生成高分辨率图像,并在生成图像上添加水印,返回处理后的图像列表。
def paint(sampler, image, prompt, seed, scale, h, w, steps, num_samples=1, callback=None, eta=0., noise_level=None):
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
model = sampler.model
seed_everything(seed)
prng = np.random.RandomState(seed)
start_code = prng.randn(num_samples, model.channels, h , w)
start_code = torch.from_numpy(start_code).to(device=device, dtype=torch.float32)
print("Creating invisible watermark encoder (see https://github.com/ShieldMnt/invisible-watermark)...")
wm = "SDV2"
wm_encoder = WatermarkEncoder()
wm_encoder.set_watermark('bytes', wm.encode('utf-8'))
with torch.no_grad(),\
torch.autocast("cuda"):
batch = make_batch_sd(image, txt=prompt, device=device, num_samples=num_samples)
c = model.cond_stage_model.encode(batch["txt"])
c_cat = list()
if isinstance(model, LatentUpscaleFinetuneDiffusion):
for ck in model.concat_keys:
cc = batch[ck]
if exists(model.reshuffle_patch_size):
assert isinstance(model.reshuffle_patch_size, int)
cc = rearrange(cc, 'b c (p1 h) (p2 w) -> b (p1 p2 c) h w',
p1=model.reshuffle_patch_size, p2=model.reshuffle_patch_size)
c_cat.append(cc)
c_cat = torch.cat(c_cat, dim=1)
# cond
cond = {"c_concat": [c_cat], "c_crossattn": [c]}
# uncond cond
uc_cross = model.get_unconditional_conditioning(num_samples, "")
uc_full = {"c_concat": [c_cat], "c_crossattn": [uc_cross]}
elif isinstance(model, LatentUpscaleDiffusion):
x_augment, noise_level = make_noise_augmentation(model, batch, noise_level)
cond = {"c_concat": [x_augment], "c_crossattn": [c], "c_adm": noise_level}
# uncond cond
uc_cross = model.get_unconditional_conditioning(num_samples, "")
uc_full = {"c_concat": [x_augment], "c_crossattn": [uc_cross], "c_adm": noise_level}
else:
raise NotImplementedError()
shape = [model.channels, h, w]
samples, intermediates = sampler.sample(
steps,
num_samples,
shape,
cond,
verbose=False,
eta=eta,
unconditional_guidance_scale=scale,
unconditional_conditioning=uc_full,
x_T=start_code,
callback=callback
)
with torch.no_grad():
x_samples_ddim = model.decode_first_stage(samples)
result = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
result = result.cpu().numpy().transpose(0, 2, 3, 1) * 255
st.text(f"upscaled image shape: {result.shape}")
return [put_watermark(Image.fromarray(img.astype(np.uint8)), wm_encoder) for img in result]
1.5 启动 Streamlit
函数 run 的功能是启动 Streamlit 应用,提供用户界面以上传图像、输入提示和调整参数,最终调用 paint 函数生成超分辨率图像并展示结果。
def run():
st.title("Stable Diffusion Upscaling")
# run via streamlit run scripts/demo/depth2img.py <path-tp-config> <path-to-ckpt>
sampler = initialize_model(sys.argv[1], sys.argv[2])
image = st.file_uploader("Image", ["jpg", "png"])
if image:
image = Image.open(image)
w, h = image.size
st.text(f"loaded input image of size ({w}, {h})")
width, height = map(lambda x: x - x % 64, (w, h)) # resize to integer multiple of 64
image = image.resize((width, height))
st.text(f"resized input image to size ({width}, {height} (w, h))")
st.image(image)
st.write(f"\n Tip: Add a description of the object that should be upscaled, e.g.: 'a professional photograph of a cat'")
prompt = st.text_input("Prompt", "a high quality professional photograph")
seed = st.number_input("Seed", min_value=0, max_value=1000000, value=0)
num_samples = st.number_input("Number of Samples", min_value=1, max_value=64, value=1)
scale = st.slider("Scale", min_value=0.1, max_value=30.0, value=9.0, step=0.1)
steps = st.slider("DDIM Steps", min_value=2, max_value=250, value=50, step=1)
eta = st.sidebar.number_input("eta (DDIM)", value=0., min_value=0., max_value=1.)
noise_level = None
if isinstance(sampler.model, LatentUpscaleDiffusion):
# TODO: make this work for all models
noise_level = st.sidebar.number_input("Noise Augmentation", min_value=0, max_value=350, value=20)
noise_level = torch.Tensor(num_samples * [noise_level]).to(sampler.model.device).long()
t_progress = st.progress(0)
def t_callback(t):
t_progress.progress(min((t + 1) / steps, 1.))
sampler.make_schedule(steps, ddim_eta=eta, verbose=True)
if st.button("Sample"):
result = paint(
sampler=sampler,
image=image,
prompt=prompt,
seed=seed,
scale=scale,
h=height, w=width, steps=steps,
num_samples=num_samples,
callback=t_callback,
noise_level=noise_level,
eta=eta
)
st.write("Result")
for image in result:
st.image(image, output_format='PNG')
if __name__ == "__main__":
run()
1.6 图像增强测试
通过下面的命令,使用Stable Diffusion对指定图像实现超分辨率(upscaling)提升处理。
python scripts/gradio/superresolution.py configs/stable-diffusion/x4-upscaling.yaml <path-to-checkpoint>
在Gradio或Streamlit界面中,可以上传要进行超分辨率处理的图像。如果您望处理合成的示例,建议将 noise_level 设置为较高的值(例如100)。执行后将看到超分辨率处理的结果,如图5-8所示,我们可以下载生成的高分辨率图像。
图5-8 图像超分辨率提升处理