Add support for resume in Textual Inversion

1 files changed, 23 insertions, 19 deletions

diff --git a/pipelines/stable_diffusion/vlpn_stable_diffusion.py b/pipelines/stable_diffusion/vlpn_stable_diffusion.py
index 141b9a7..707b639 100644
--- a/pipelines/stable_diffusion/vlpn_stable_diffusion.py
+++ b/pipelines/stable_diffusion/vlpn_stable_diffusion.py
@@ -421,25 +421,29 @@ class VlpnStableDiffusion(DiffusionPipeline):
         extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
 
         # 7. Denoising loop
-        for i, t in enumerate(self.progress_bar(timesteps)):
-            # 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)
-
-            # predict the noise residual
-            noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=text_embeddings).sample
-
-            # perform guidance
-            if do_classifier_free_guidance:
-                noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                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, latents, **extra_step_kwargs).prev_sample
-
-            # call the callback, if provided
-            if callback is not None and i % callback_steps == 0:
-                callback(i, t, latents)
+        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
+        with self.progress_bar(total=num_inference_steps) as progress_bar:
+            for i, t in enumerate(timesteps):
+                # 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)
+
+                # predict the noise residual
+                noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=text_embeddings).sample
+
+                # perform guidance
+                if do_classifier_free_guidance:
+                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
+                    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, latents, **extra_step_kwargs).prev_sample
+
+                # call the callback, if provided
+                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
+                    progress_bar.update()
+                    if callback is not None and i % callback_steps == 0:
+                        callback(i, t, latents)
 
         # 8. Post-processing
         image = self.decode_latents(latents)