Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 17:24:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

enable basic img2img

Browse Source
This commit is contained in:
Vladimir Mandic
2023-07-10 11:44:52 -04:00
parent 768daecd74
commit 75a8c1f9d0
4 changed files with 23 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/processing.py
+6 -7
View File
@@ -225,14 +225,13 @@ class StableDiffusionProcessing:
# identify itself with a field common to all models. The conditioning_key is also hybrid.
if backend == Backend.DIFFUSERS:
log.warning('Diffusers not implemented: img2img_image_conditioning')
return None
if isinstance(self.sd_model, LatentDepth2ImageDiffusion):
return self.depth2img_image_conditioning(source_image)
if self.sd_model.cond_stage_key == "edit":
if hasattr(self.sd_model, 'cond_stage_key') and self.sd_model.cond_stage_key == "edit":
return self.edit_image_conditioning(source_image)
if self.sampler.conditioning_key in {'hybrid', 'concat'}:
if hasattr(self.sampler, 'conditioning_key') and self.sampler.conditioning_key in {'hybrid', 'concat'}:
return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
if self.sampler.conditioning_key == "crossattn-adm":
if hasattr(self.sampler, 'conditioning_key') and self.sampler.conditioning_key == "crossattn-adm":
return self.unclip_image_conditioning(source_image)
# Dummy zero conditioning if we're not using inpainting or depth model.
return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)
@@ -752,7 +751,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
x_samples_ddim = output.images
if p.enable_hr:
if p.is_hr_pass:
log.warning('Diffusers not implemented: hires fix')
if lora_state['active']:
@@ -1130,8 +1129,8 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
if backend == Backend.ORIGINAL:
self.init_latent = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image))
else:
# we don't pre-encode the latents for diffusers to allow the UI to stay general for different model types
self.init_latent = None
# TODO Diffusers don't pre-encode the latents for diffusers to allow the UI to stay general for different model types
self.init_latent = torch.Tensor(1)
if self.resize_mode == 3:
self.init_latent = torch.nn.functional.interpolate(self.init_latent, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")