.

options/Video_model/Model.py

@@ -53,9 +53,21 @@ def Video(
     base_count = len(glob(os.path.join(output_folder, "*.mp4")))
     video_path = os.path.join(output_folder, f"{base_count:06d}.mp4")
 
-    # Use float32 for image processing to avoid BFloat16 errors
-    image = image.convert("RGB")  # Ensure image is in RGB format
-    with torch.autocast(device, dtype=torch.float32):
+    # Only use autocast if on CUDA, otherwise run without it on CPU
+    if device == "cuda":
+        with torch.autocast(device_type='cuda', dtype=torch.float16):
+            frames = pipeline(
+                image, height=height, width=width,
+                num_inference_steps=num_inference_steps,
+                min_guidance_scale=min_guidance_scale,
+                max_guidance_scale=max_guidance_scale,
+                num_frames=num_frames, fps=fps, motion_bucket_id=motion_bucket_id,
+                decode_chunk_size=8,
+                noise_aug_strength=0.02,
+                generator=generator,
+            ).frames[0]
+    else:
+        # No autocast for CPU since it doesn't support float32 in autocast
         frames = pipeline(
             image, height=height, width=width,
             num_inference_steps=num_inference_steps,