Skip to content

Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation

Fix a typo.

HELLORPG21b0c271aaa6
diff --git a/README.md b/README.md
index 3be3c87..87dbc07 100644
--- a/README.md
+++ b/README.md
@@ -166,7 +166,7 @@ By default, inference selects the longest valid tail segment of the input video
as the prefix. Use `--v2v_context_latents` to set the prefix length manually.
See the [inference documentation](docs/inference.md) for details.
-### General Text-and-Image-to-Video Generation
+### Text-and-Image-to-Video Generation
Run the following single-GPU example from the repository root. It generates a 5-second video using the 1.3B FCP model, the provided sailboat image and its matching prompt file: