[Wan2.2] Optimize memory usage with conditional transformer loading (#980)

Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>

examples/offline_inference/text_to_video/text_to_video.md

@@ -26,7 +26,7 @@ Key arguments:
 - `--num_frames`: Number of frames (Wan default is 81).
 - `--guidance_scale` and `--guidance_scale_high`: CFG scale (applied to low/high).
 - `--negative_prompt`: optional list of artifacts to suppress (the PR demo used a long Chinese string).
-- `--boundary_ratio`: Boundary split ratio for low/high DiT.
+- `--boundary_ratio`: Boundary split ratio for low/high DiT. Default `0.875` uses both transformers for best quality. Set to `1.0` to load only the low-noise transformer (saves noticeable memory with good quality, recommended if memory is limited). Set to `0.0` loads only the high-noise transformer (not recommended, lower quality).
 - `--fps`: frames per second for the saved MP4 (requires `diffusers` export_to_video).
 - `--output`: path to save the generated video.
 - `--vae_use_slicing`: enable VAE slicing for memory optimization.

examples/offline_inference/text_to_video/text_to_video.py

@@ -32,7 +32,12 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--width", type=int, default=1280, help="Video width.")
     parser.add_argument("--num_frames", type=int, default=81, help="Number of frames (Wan default is 81).")
     parser.add_argument("--num_inference_steps", type=int, default=40, help="Sampling steps.")
-    parser.add_argument("--boundary_ratio", type=float, default=0.875, help="Boundary split ratio for low/high DiT.")
+    parser.add_argument(
+        "--boundary_ratio",
+        type=float,
+        default=0.875,
+        help="Boundary split ratio for low/high DiT. Default 0.875 uses both transformers for best quality. Set to 1.0 to load only the low-noise transformer (saves noticeable memory with good quality, recommended if memory is limited).",
+    )
     parser.add_argument(
         "--flow_shift", type=float, default=5.0, help="Scheduler flow_shift (5.0 for 720p, 12.0 for 480p)."
     )