Re-enable TQDM (reverts #11)

TQDM issues should now be fixed.
This reverts https://huggingface.co/spaces/TencentARC/PhotoMaker/discussions/11

pipeline.py

@@ -398,50 +398,51 @@ class PhotoMakerStableDiffusionXLPipeline(StableDiffusionXLPipeline):
 
         # 11. Denoising loop
         num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
-
-        for i, t in enumerate(timesteps):
-            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)
-
-            if i <= start_merge_step:
-                current_prompt_embeds = torch.cat(
-                    [negative_prompt_embeds, prompt_embeds_text_only], dim=0
-                )
-                add_text_embeds = torch.cat([negative_pooled_prompt_embeds, pooled_prompt_embeds_text_only], dim=0)
-            else:
-                current_prompt_embeds = torch.cat(
-                    [negative_prompt_embeds, prompt_embeds], dim=0
+        with self.progress_bar(total=num_inference_steps) as progress_bar:
+            for i, t in enumerate(timesteps):
+                latent_model_input = (
+                    torch.cat([latents] * 2) if do_classifier_free_guidance else latents
                 )
-                add_text_embeds = torch.cat([negative_pooled_prompt_embeds, pooled_prompt_embeds], dim=0)
-            # predict the noise residual
-            added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
-            noise_pred = self.unet(
-                latent_model_input,
-                t,
-                encoder_hidden_states=current_prompt_embeds,
-                cross_attention_kwargs=cross_attention_kwargs,
-                added_cond_kwargs=added_cond_kwargs,
-                return_dict=False,
-            )[0]
-
-            # 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)
-
-            if do_classifier_free_guidance and guidance_rescale > 0.0:
-                # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
-                noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=guidance_rescale)
-
-            # compute the previous noisy sample x_t -> x_t-1
-            latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
-
-            # call the callback, if provided
-            if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
-                if callback is not None and i % callback_steps == 0:
-                    callback(i, t, latents)
+                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
+
+                if i <= start_merge_step:
+                    current_prompt_embeds = torch.cat(
+                        [negative_prompt_embeds, prompt_embeds_text_only], dim=0
+                    )
+                    add_text_embeds = torch.cat([negative_pooled_prompt_embeds, pooled_prompt_embeds_text_only], dim=0)
+                else:
+                    current_prompt_embeds = torch.cat(
+                        [negative_prompt_embeds, prompt_embeds], dim=0
+                    )
+                    add_text_embeds = torch.cat([negative_pooled_prompt_embeds, pooled_prompt_embeds], dim=0)
+                # predict the noise residual
+                added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
+                noise_pred = self.unet(
+                    latent_model_input,
+                    t,
+                    encoder_hidden_states=current_prompt_embeds,
+                    cross_attention_kwargs=cross_attention_kwargs,
+                    added_cond_kwargs=added_cond_kwargs,
+                    return_dict=False,
+                )[0]
+
+                # 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)
+
+                if do_classifier_free_guidance and guidance_rescale > 0.0:
+                    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
+                    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=guidance_rescale)
+
+                # compute the previous noisy sample x_t -> x_t-1
+                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
+
+                # 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)
 
         # make sure the VAE is in float32 mode, as it overflows in float16
         if self.vae.dtype == torch.float16 and self.vae.config.force_upcast: