add tqdm again to flux pipeline.

Author: jfacevedo-google

src/diffusers/pipelines/flux/pipeline_flux.py

@@ -708,48 +708,48 @@ def __call__(
             guidance = None
 
         # 6. Denoising loop
-        #with self.progress_bar(total=num_inference_steps) as progress_bar:
-        for i, t in enumerate(timesteps):
-            if self.interrupt:
-                continue
-
-            # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
-            timestep = t.expand(latents.shape[0]).to(latents.dtype)
-
-            noise_pred = self.transformer(
-                hidden_states=latents,
-                timestep=timestep / 1000,
-                guidance=guidance,
-                pooled_projections=pooled_prompt_embeds,
-                encoder_hidden_states=prompt_embeds,
-                txt_ids=text_ids,
-                img_ids=latent_image_ids,
-                joint_attention_kwargs=self.joint_attention_kwargs,
-                return_dict=False,
-            )[0]
-
-            # compute the previous noisy sample x_t -> x_t-1
-            latents_dtype = latents.dtype
-            
-            latents = self.scheduler.step(noise_pred, t, latents, return_dict=False)[0]
-
-            if latents.dtype != latents_dtype:
-                if torch.backends.mps.is_available():
-                    # some platforms (eg. apple mps) misbehave due to a pytorch bug: https://github.com/pytorch/pytorch/pull/99272
-                    latents = latents.to(latents_dtype)
-
-            if callback_on_step_end is not None:
-                callback_kwargs = {}
-                for k in callback_on_step_end_tensor_inputs:
-                    callback_kwargs[k] = locals()[k]
-                callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)
-
-                latents = callback_outputs.pop("latents", latents)
-                prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
+        with self.progress_bar(total=num_inference_steps) as progress_bar:
+            for i, t in enumerate(timesteps):
+                if self.interrupt:
+                    continue
+
+                # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
+                timestep = t.expand(latents.shape[0]).to(latents.dtype)
+
+                noise_pred = self.transformer(
+                    hidden_states=latents,
+                    timestep=timestep / 1000,
+                    guidance=guidance,
+                    pooled_projections=pooled_prompt_embeds,
+                    encoder_hidden_states=prompt_embeds,
+                    txt_ids=text_ids,
+                    img_ids=latent_image_ids,
+                    joint_attention_kwargs=self.joint_attention_kwargs,
+                    return_dict=False,
+                )[0]
+
+                # compute the previous noisy sample x_t -> x_t-1
+                latents_dtype = latents.dtype
+                
+                latents = self.scheduler.step(noise_pred, t, latents, return_dict=False)[0]
+
+                if latents.dtype != latents_dtype:
+                    if torch.backends.mps.is_available():
+                        # some platforms (eg. apple mps) misbehave due to a pytorch bug: https://github.com/pytorch/pytorch/pull/99272
+                        latents = latents.to(latents_dtype)
+
+                if callback_on_step_end is not None:
+                    callback_kwargs = {}
+                    for k in callback_on_step_end_tensor_inputs:
+                        callback_kwargs[k] = locals()[k]
+                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)
+
+                    latents = callback_outputs.pop("latents", latents)
+                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
 
                 # 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 i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
+                    progress_bar.update()
 
                 if XLA_AVAILABLE:
                     xm.mark_step()