mirror/stable-diffusion-webui
2
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2024-12-21 07:30:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

bugfix: save image for hires fix BEFORE upscaling latent space

Browse Source
This commit is contained in:
AUTOMATIC 2022-11-04 10:45:34 +03:00
parent 321e13ca17
commit f674c488d9
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
modules/processing.py
View File

@ -665,6 +665,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix") images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix")
if opts.use_scale_latent_for_hires_fix: if opts.use_scale_latent_for_hires_fix:
for i in range(samples.shape[0]):
save_intermediate(samples, i)
samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear") samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
# Avoid making the inpainting conditioning unless necessary as # Avoid making the inpainting conditioning unless necessary as
@ -673,9 +676,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
image_conditioning = self.img2img_image_conditioning(decode_first_stage(self.sd_model, samples), samples) image_conditioning = self.img2img_image_conditioning(decode_first_stage(self.sd_model, samples), samples)
else: else:
image_conditioning = self.txt2img_image_conditioning(samples) image_conditioning = self.txt2img_image_conditioning(samples)
for i in range(samples.shape[0]):
save_intermediate(samples, i)
else: else:
decoded_samples = decode_first_stage(self.sd_model, samples) decoded_samples = decode_first_stage(self.sd_model, samples)
lowres_samples = torch.clamp((decoded_samples + 1.0) / 2.0, min=0.0, max=1.0) lowres_samples = torch.clamp((decoded_samples + 1.0) / 2.0, min=0.0, max=1.0)