diff options
Diffstat (limited to 'modules/sd_samplers.py')
| -rw-r--r-- | modules/sd_samplers.py | 47 |
1 files changed, 33 insertions, 14 deletions
diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index d26e48dc..e904d860 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -9,7 +9,7 @@ import k_diffusion.sampling import torchsde._brownian.brownian_interval
import ldm.models.diffusion.ddim
import ldm.models.diffusion.plms
-from modules import prompt_parser, devices, processing, images
+from modules import prompt_parser, devices, processing, images, sd_vae_approx
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
@@ -106,20 +106,32 @@ def setup_img2img_steps(p, steps=None): return steps, t_enc
-def single_sample_to_image(sample):
- x_sample = processing.decode_first_stage(shared.sd_model, sample.unsqueeze(0))[0]
+approximation_indexes = {"Full": 0, "Approx NN": 1, "Approx cheap": 2}
+
+
+def single_sample_to_image(sample, approximation=None):
+ if approximation is None:
+ approximation = approximation_indexes.get(opts.show_progress_type, 0)
+
+ if approximation == 2:
+ x_sample = sd_vae_approx.cheap_approximation(sample)
+ elif approximation == 1:
+ x_sample = sd_vae_approx.model()(sample.to(devices.device, devices.dtype).unsqueeze(0))[0].detach()
+ else:
+ x_sample = processing.decode_first_stage(shared.sd_model, sample.unsqueeze(0))[0]
+
x_sample = torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0)
x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2)
x_sample = x_sample.astype(np.uint8)
return Image.fromarray(x_sample)
-def sample_to_image(samples, index=0):
- return single_sample_to_image(samples[index])
+def sample_to_image(samples, index=0, approximation=None):
+ return single_sample_to_image(samples[index], approximation)
-def samples_to_image_grid(samples):
- return images.image_grid([single_sample_to_image(sample) for sample in samples])
+def samples_to_image_grid(samples, approximation=None):
+ return images.image_grid([single_sample_to_image(sample, approximation) for sample in samples])
def store_latent(decoded):
@@ -288,6 +300,16 @@ class CFGDenoiser(torch.nn.Module): self.init_latent = None
self.step = 0
+ def combine_denoised(self, x_out, conds_list, uncond, cond_scale):
+ denoised_uncond = x_out[-uncond.shape[0]:]
+ denoised = torch.clone(denoised_uncond)
+
+ for i, conds in enumerate(conds_list):
+ for cond_index, weight in conds:
+ denoised[i] += (x_out[cond_index] - denoised_uncond[i]) * (weight * cond_scale)
+
+ return denoised
+
def forward(self, x, sigma, uncond, cond, cond_scale, image_cond):
if state.interrupted or state.skipped:
raise InterruptedException
@@ -329,12 +351,7 @@ class CFGDenoiser(torch.nn.Module): x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond={"c_crossattn": [uncond], "c_concat": [image_cond_in[-uncond.shape[0]:]]})
- denoised_uncond = x_out[-uncond.shape[0]:]
- denoised = torch.clone(denoised_uncond)
-
- for i, conds in enumerate(conds_list):
- for cond_index, weight in conds:
- denoised[i] += (x_out[cond_index] - denoised_uncond[i]) * (weight * cond_scale)
+ denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
if self.mask is not None:
denoised = self.init_latent * self.mask + self.nmask * denoised
@@ -448,7 +465,9 @@ class KDiffusionSampler: if p.sampler_noise_scheduler_override:
sigmas = p.sampler_noise_scheduler_override(steps)
elif self.config is not None and self.config.options.get('scheduler', None) == 'karras':
- sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=0.1, sigma_max=10, device=shared.device)
+ sigma_min, sigma_max = (0.1, 10) if opts.use_old_karras_scheduler_sigmas else (self.model_wrap.sigmas[0].item(), self.model_wrap.sigmas[-1].item())
+
+ sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=sigma_min, sigma_max=sigma_max, device=shared.device)
else:
sigmas = self.model_wrap.get_sigmas(steps)
|