Modify FlowMatch Scale Noise

src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3_img2img.py

@@ -852,7 +852,7 @@ def __call__(
         # 4. Prepare timesteps
         timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, timesteps)
         timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, strength, device)
-        latent_timestep = timesteps[:1].repeat(batch_size * num_inference_steps)
+        latent_timestep = timesteps[:1].repeat(batch_size * num_images_per_prompt)
 
         # 5. Prepare latent variables
         if latents is None:

src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py

@@ -129,7 +129,31 @@ def scale_noise(
         if self.step_index is None:
             self._init_step_index(timestep)
 
-        sigma = self.sigmas[self.step_index]
+        # Make sure sigmas and timesteps have the same device and dtype as original_samples
+        sigmas = self.sigmas.to(device=sample.device, dtype=sample.dtype)
+
+        if sample.device.type == "mps" and torch.is_floating_point(timestep):
+            # mps does not support float64
+            schedule_timesteps = self.timesteps.to(sample.device, dtype=torch.float32)
+            timestep = timestep.to(sample.device, dtype=torch.float32)
+        else:
+            schedule_timesteps = self.timesteps.to(sample.device)
+            timestep = timestep.to(sample.device)
+
+        # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
+        if self.begin_index is None:
+            step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timestep]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timestep.shape[0]
+        else:
+            # add noise is called before first denoising step to create initial latent(img2img)
+            step_indices = [self.begin_index] * timestep.shape[0]
+
+        sigma = sigmas[step_indices].flatten()
+        while len(sigma.shape) < len(sample.shape):
+            sigma = sigma.unsqueeze(-1)
+
         sample = sigma * noise + (1.0 - sigma) * sample
 
         return sample