testing flux

Author: entrpn

src/diffusers/pipelines/flux/pipeline_flux.py

@@ -874,68 +874,68 @@ def __call__(
             )
 
         # 6. Denoising loop
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            for i, t in enumerate(timesteps):
-                if self.interrupt:
-                    continue
-
-                if image_embeds is not None:
-                    self._joint_attention_kwargs["ip_adapter_image_embeds"] = image_embeds
-                # 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(
+        #with self.progress_bar(total=num_inference_steps) as progress_bar:
+        for i, t in enumerate(timesteps):
+            if self.interrupt:
+                continue
+
+            if image_embeds is not None:
+                self._joint_attention_kwargs["ip_adapter_image_embeds"] = image_embeds
+            # 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]
+
+            if do_true_cfg:
+                if negative_image_embeds is not None:
+                    self._joint_attention_kwargs["ip_adapter_image_embeds"] = negative_image_embeds
+                neg_noise_pred = self.transformer(
                     hidden_states=latents,
                     timestep=timestep / 1000,
                     guidance=guidance,
-                    pooled_projections=pooled_prompt_embeds,
-                    encoder_hidden_states=prompt_embeds,
+                    pooled_projections=negative_pooled_prompt_embeds,
+                    encoder_hidden_states=negative_prompt_embeds,
                     txt_ids=text_ids,
                     img_ids=latent_image_ids,
                     joint_attention_kwargs=self.joint_attention_kwargs,
                     return_dict=False,
                 )[0]
+                noise_pred = neg_noise_pred + true_cfg_scale * (noise_pred - neg_noise_pred)
+
+            # 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 do_true_cfg:
-                    if negative_image_embeds is not None:
-                        self._joint_attention_kwargs["ip_adapter_image_embeds"] = negative_image_embeds
-                    neg_noise_pred = self.transformer(
-                        hidden_states=latents,
-                        timestep=timestep / 1000,
-                        guidance=guidance,
-                        pooled_projections=negative_pooled_prompt_embeds,
-                        encoder_hidden_states=negative_prompt_embeds,
-                        txt_ids=text_ids,
-                        img_ids=latent_image_ids,
-                        joint_attention_kwargs=self.joint_attention_kwargs,
-                        return_dict=False,
-                    )[0]
-                    noise_pred = neg_noise_pred + true_cfg_scale * (noise_pred - neg_noise_pred)
-
-                # 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 XLA_AVAILABLE:
-                    xm.mark_step()
+            if XLA_AVAILABLE:
+                xm.mark_step()
 
         if output_type == "latent":
             image = latents