instruct-pix2pix support

2 files changed, 5 insertions, 5 deletions

diff --git a/modules/processing.py b/modules/processing.py
index e544c2e1..f299e04d 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -186,7 +186,7 @@ class StableDiffusionProcessing:
         return conditioning

 

     def edit_image_conditioning(self, source_image):

-        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))

+        conditioning_image = self.sd_model.encode_first_stage(source_image).mode()

 

         return conditioning_image

 

diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py
index aa7f106b..31ee22d3 100644
--- a/modules/sd_samplers_kdiffusion.py
+++ b/modules/sd_samplers_kdiffusion.py
@@ -77,9 +77,9 @@ class CFGDenoiser(torch.nn.Module):
         batch_size = len(conds_list)

         repeats = [len(conds_list[i]) for i in range(batch_size)]

 

-        x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])

-        image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])

-        sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])

+        x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x] + [x])

+        sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma] + [sigma])

+        image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond] + [image_cond])

 

         denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)

         cfg_denoiser_callback(denoiser_params)

@@ -88,7 +88,7 @@ class CFGDenoiser(torch.nn.Module):
         sigma_in = denoiser_params.sigma

 

         if tensor.shape[1] == uncond.shape[1]:

-            cond_in = torch.cat([tensor, uncond])

+            cond_in = torch.cat([tensor, uncond, uncond])

 

             if shared.batch_cond_uncond:

                 x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})