if noise_inds is None:

return torch.randn(latent_image.size(), dtype=torch.float32, layout=latent_image.layout, generator=generator, device="cpu").to(dtype=latent_image.dtype)

unique_inds, inverse = np.unique(noise_inds, return_inverse=True)

noises = []

for i in range(unique_inds[-1]+1):

noise = torch.randn([1] + list(latent_image.size())[1:], dtype=torch.float32, layout=latent_image.layout, generator=generator, device="cpu").to(dtype=latent_image.dtype)

if i in unique_inds:

noises.append(noise)

noises = [noises[i] for i in inverse]

"""

generator = torch.manual_seed(seed)

if latent_image.is_nested:

tensors = latent_image.unbind()

noises = []

for t in tensors:

noises.append(prepare_noise_inner(t, generator, noise_inds))

noises = comfy.nested_tensor.NestedTensor(noises)

else:

noises = prepare_noise_inner(latent_image, generator, noise_inds)

if latent_image.is_nested:

return latent_image

latent_format = model.get_model_object("latent_format")

is_empty = torch.count_nonzero(latent_image) == 0

if is_empty:

if latent_format.latent_channels != latent_image.shape[1]:

latent_image = comfy.utils.repeat_to_batch_size(latent_image, latent_format.latent_channels, dim=1)

if downscale_ratio_spacial is not None:

if downscale_ratio_spacial != latent_format.spacial_downscale_ratio:

ratio = downscale_ratio_spacial / latent_format.spacial_downscale_ratio

latent_image = comfy.utils.common_upscale(latent_image, round(latent_image.shape[-1] * ratio), round(latent_image.shape[-2] * ratio), "nearest-exact", crop="disabled")

if latent_format.latent_dimensions == 3 and latent_image.ndim == 4:

latent_image = latent_image.unsqueeze(2)

if is_empty and downscale_ratio_temporal is not None:

if downscale_ratio_temporal != latent_format.temporal_downscale_ratio:

ratio = downscale_ratio_temporal / latent_format.temporal_downscale_ratio

new_t = max(1, round(latent_image.shape[2] * ratio))

latent_image = comfy.utils.repeat_to_batch_size(latent_image, new_t, dim=2)

if is_empty:

latent_image = latent_format.fix_empty_latent(latent_image)

sampler = comfy.samplers.KSampler(model, steps=steps, device=model.load_device, sampler=sampler_name, scheduler=scheduler, denoise=denoise, model_options=model.model_options)

samples = sampler.sample(noise, positive, negative, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)

samples = samples.to(device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype())