diff options
| author | AUTOMATIC <16777216c@gmail.com> | 2022-09-20 16:32:26 +0000 |
|---|---|---|
| committer | AUTOMATIC <16777216c@gmail.com> | 2022-09-20 16:32:26 +0000 |
| commit | 06cd20610765aeb563700f377f1698a6e981b17d (patch) | |
| tree | 065c63fb15a3787dfc4550e0055e185487bfecab /modules/processing.py | |
| parent | 2c9777fcc7a2c0d3b8c64807b6a1fc8bf360d171 (diff) | |
| download | stable-diffusion-webui-gfx803-06cd20610765aeb563700f377f1698a6e981b17d.tar.gz stable-diffusion-webui-gfx803-06cd20610765aeb563700f377f1698a6e981b17d.tar.bz2 stable-diffusion-webui-gfx803-06cd20610765aeb563700f377f1698a6e981b17d.zip | |
Enable neural network upscalers for highres. fix
Diffstat (limited to 'modules/processing.py')
| -rw-r--r-- | modules/processing.py | 22 |
1 files changed, 21 insertions, 1 deletions
diff --git a/modules/processing.py b/modules/processing.py index 2bc19f6b..c9ba6eb3 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -450,7 +450,27 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
else:
decoded_samples = self.sd_model.decode_first_stage(samples)
- decoded_samples = torch.nn.functional.interpolate(decoded_samples, size=(self.height, self.width), mode="bilinear")
+
+ if opts.upscaler_for_hires_fix is None or opts.upscaler_for_hires_fix == "None":
+ decoded_samples = torch.nn.functional.interpolate(decoded_samples, size=(self.height, self.width), mode="bilinear")
+ else:
+ lowres_samples = torch.clamp((decoded_samples + 1.0) / 2.0, min=0.0, max=1.0)
+
+ batch_images = []
+ for i, x_sample in enumerate(lowres_samples):
+ x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2)
+ x_sample = x_sample.astype(np.uint8)
+ image = Image.fromarray(x_sample)
+ upscaler = [x for x in shared.sd_upscalers if x.name == opts.upscaler_for_hires_fix][0]
+ image = upscaler.upscale(image, self.width, self.height)
+ image = np.array(image).astype(np.float32) / 255.0
+ image = np.moveaxis(image, 2, 0)
+ batch_images.append(image)
+
+ decoded_samples = torch.from_numpy(np.array(batch_images))
+ decoded_samples = decoded_samples.to(shared.device)
+ decoded_samples = 2. * decoded_samples - 1.
+
samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples))
shared.state.nextjob()
|