diff options
Diffstat (limited to 'modules/sd_samplers.py')
| -rw-r--r-- | modules/sd_samplers.py | 40 |
1 files changed, 27 insertions, 13 deletions
diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index d26e48dc..27ef4ff8 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -106,20 +106,29 @@ 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]
+def single_sample_to_image(sample, approximation=False):
+ if approximation:
+ # https://discuss.huggingface.co/t/decoding-latents-to-rgb-without-upscaling/23204/2
+ coefs = torch.tensor(
+ [[ 0.298, 0.207, 0.208],
+ [ 0.187, 0.286, 0.173],
+ [-0.158, 0.189, 0.264],
+ [-0.184, -0.271, -0.473]]).to(sample.device)
+ x_sample = torch.einsum("lxy,lr -> rxy", sample, coefs)
+ 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=False):
+ 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=False):
+ return images.image_grid([single_sample_to_image(sample, approximation) for sample in samples])
def store_latent(decoded):
@@ -127,7 +136,7 @@ def store_latent(decoded): if opts.show_progress_every_n_steps > 0 and shared.state.sampling_step % opts.show_progress_every_n_steps == 0:
if not shared.parallel_processing_allowed:
- shared.state.current_image = sample_to_image(decoded)
+ shared.state.current_image = sample_to_image(decoded, approximation=opts.show_progress_approximate)
class InterruptedException(BaseException):
@@ -288,6 +297,16 @@ 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 +348,7 @@ 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
|