with torch.no_grad():

input_image = HWC3(input_image)

detected_map = apply_uniformer(resize_image(input_image, detect_resolution))

img = resize_image(input_image, image_resolution)

H, W, C = img.shape

detected_map = cv2.resize(detected_map, (W, H), interpolation=cv2.INTER_NEAREST)

control = torch.from_numpy(detected_map.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)]