Update

1 files changed, 3 insertions, 2 deletions

diff --git a/pipelines/stable_diffusion/vlpn_stable_diffusion.py b/pipelines/stable_diffusion/vlpn_stable_diffusion.py
index fc12355..cd5ae7e 100644
--- a/pipelines/stable_diffusion/vlpn_stable_diffusion.py
+++ b/pipelines/stable_diffusion/vlpn_stable_diffusion.py
@@ -203,6 +203,7 @@ class VlpnStableDiffusion(DiffusionPipeline):
         # However this currently doesn't work in `mps`.
         latents_dtype = text_embeddings.dtype
         latents_shape = (batch_size, self.unet.in_channels, height // 8, width // 8)
+
         if latents is None:
             if self.device.type == "mps":
                 # randn does not exist on mps
@@ -264,7 +265,7 @@ class VlpnStableDiffusion(DiffusionPipeline):
         for i, t in enumerate(self.progress_bar(timesteps_tensor)):
             # expand the latents if we are doing classifier free guidance
             latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
-            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t, i)
+            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
 
             # predict the noise residual
             noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=text_embeddings).sample
@@ -275,7 +276,7 @@ class VlpnStableDiffusion(DiffusionPipeline):
                 noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
 
             # compute the previous noisy sample x_t -> x_t-1
-            latents = self.scheduler.step(noise_pred, t, i, latents, **extra_step_kwargs).prev_sample
+            latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs).prev_sample
 
         # scale and decode the image latents with vae
         latents = 1 / 0.18215 * latents