Apply np.array to provided sigmas

Author: hlky

src/diffusers/pipelines/flux/pipeline_flux.py

@@ -699,7 +699,7 @@ def __call__(
         )
 
         # 5. Prepare timesteps
-        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
+        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else np.array(sigmas)
         image_seq_len = latents.shape[1]
         mu = calculate_shift(
             image_seq_len,

src/diffusers/pipelines/flux/pipeline_flux_control.py

@@ -799,7 +799,7 @@ def __call__(
         )
 
         # 5. Prepare timesteps
-        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
+        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else np.array(sigmas)
         image_seq_len = latents.shape[1]
         mu = calculate_shift(
             image_seq_len,

src/diffusers/pipelines/flux/pipeline_flux_control_img2img.py

@@ -805,7 +805,7 @@ def __call__(
         )
 
         # 4.Prepare timesteps
-        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
+        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else np.array(sigmas)
         image_seq_len = (int(height) // self.vae_scale_factor // 2) * (int(width) // self.vae_scale_factor // 2)
         mu = calculate_shift(
             image_seq_len,

src/diffusers/pipelines/flux/pipeline_flux_controlnet.py

@@ -872,7 +872,7 @@ def __call__(
         )
 
         # 5. Prepare timesteps
-        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
+        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else np.array(sigmas)
         image_seq_len = latents.shape[1]
         mu = calculate_shift(
             image_seq_len,

src/diffusers/pipelines/flux/pipeline_flux_controlnet_image_to_image.py

@@ -860,7 +860,7 @@ def __call__(
             control_mode = torch.tensor(control_mode_).to(device, dtype=torch.long)
             control_mode = control_mode.reshape([-1, 1])
 
-        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
+        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else np.array(sigmas)
         image_seq_len = (int(height) // self.vae_scale_factor // 2) * (int(width) // self.vae_scale_factor // 2)
         mu = calculate_shift(
             image_seq_len,

src/diffusers/pipelines/flux/pipeline_flux_controlnet_inpainting.py

@@ -1011,7 +1011,7 @@ def __call__(
 
         # 6. Prepare timesteps
 
-        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
+        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else np.array(sigmas)
         image_seq_len = (int(global_height) // self.vae_scale_factor // 2) * (
             int(global_width) // self.vae_scale_factor // 2
         )

src/diffusers/pipelines/flux/pipeline_flux_fill.py

@@ -878,7 +878,7 @@ def __call__(
             masked_image_latents = torch.cat((masked_image_latents, mask), dim=-1)
 
         # 6. Prepare timesteps
-        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
+        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else np.array(sigmas)
         image_seq_len = latents.shape[1]
         mu = calculate_shift(
             image_seq_len,

src/diffusers/pipelines/flux/pipeline_flux_img2img.py

@@ -742,7 +742,7 @@ def __call__(
         )
 
         # 4.Prepare timesteps
-        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
+        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else np.array(sigmas)
         image_seq_len = (int(height) // self.vae_scale_factor // 2) * (int(width) // self.vae_scale_factor // 2)
         mu = calculate_shift(
             image_seq_len,

src/diffusers/pipelines/flux/pipeline_flux_inpaint.py

@@ -873,7 +873,7 @@ def __call__(
         )
 
         # 4.Prepare timesteps
-        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
+        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else np.array(sigmas)
         image_seq_len = (int(height) // self.vae_scale_factor // 2) * (int(width) // self.vae_scale_factor // 2)
         mu = calculate_shift(
             image_seq_len,